{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/method/3d-convolution","slug":"3d-convolution","name":"3D Convolution","full_name":"3D Convolution","full_name_withheld":false,"description_markdown":"A **3D Convolution** is a type of [convolution](https://paperswithcode.com/method/convolution) where the kernel slides in 3 dimensions as opposed to 2 dimensions with 2D convolutions. One example use case is medical imaging where a model is constructed using 3D image slices. Additionally video based data has an additional temporal dimension over images making it suitable for this module. \r\n\r\nImage: Lung nodule detection based on 3D convolutional neural networks, Fan et al","description_state":"present","introduced_year":2015,"introduced_by":{"title":null,"paper":null,"first_author":null,"n_authors":0,"url_abs":null,"archive_paper_url":null},"source":{"url":null,"title":null,"url_on_a_paper_host":false},"code_snippet_url":"https://github.com/pytorch/pytorch/blob/73642d9425a358b51a683cf6f95852d06cba1096/torch/nn/modules/conv.py#L421","code_snippet_url_on_a_code_host":true,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"Convolutions","url":"/methods/category/convolutions","pwc_aliases":[]}],"n_papers_tagged":208,"archive_num_papers":208,"papers_newest_first":[{"paper":null,"slug":"manipulating-elasto-plastic-objects-with-3d","title":"Manipulating Elasto-Plastic Objects With 3D Occupancy and Learning-Based Predictive Control","date":"2025-05-22","arxiv_id":"2505.16249","n_code_links":0,"syntology":null},{"paper":"/paper/handreader-advanced-techniques-for-efficient","slug":"handreader-advanced-techniques-for-efficient","title":"HandReader: Advanced Techniques for Efficient Fingerspelling Recognition","date":"2025-05-15","arxiv_id":"2505.10267","n_code_links":1,"syntology":null},{"paper":null,"slug":"unimamba-unified-spatial-channel","title":"UniMamba: Unified Spatial-Channel Representation Learning with Group-Efficient Mamba for LiDAR-based 3D Object Detection","date":"2025-03-15","arxiv_id":"2503.12009","n_code_links":0,"syntology":null},{"paper":null,"slug":"billnet-a-binarized-conv3d-lstm-network-with","title":"BILLNET: A Binarized Conv3D-LSTM Network with Logic-gated residual architecture for hardware-efficient video inference","date":"2025-01-24","arxiv_id":"2501.14495","n_code_links":0,"syntology":null},{"paper":null,"slug":"swin-x2s-reconstructing-3d-shape-from-2d","title":"Swin-X2S: Reconstructing 3D Shape from 2D Biplanar X-ray with Swin Transformers","date":"2025-01-10","arxiv_id":"2501.05961","n_code_links":0,"syntology":null},{"paper":null,"slug":"superlightnet-lightweight-parameter","title":"SuperLightNet: Lightweight Parameter Aggregation Network for Multimodal Brain Tumor Segmentation","date":"2025-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/asdnb-merging-face-with-body-cues-for-robust","slug":"asdnb-merging-face-with-body-cues-for-robust","title":"ASDnB: Merging Face with Body Cues For Robust Active Speaker Detection","date":"2024-12-11","arxiv_id":"2412.08594","n_code_links":1,"syntology":null},{"paper":null,"slug":"lightweight-spatial-embedding-for-vision","title":"Lightweight Spatial Embedding for Vision-based 3D Occupancy Prediction","date":"2024-12-08","arxiv_id":"2412.05976","n_code_links":0,"syntology":null},{"paper":"/paper/intensity-spatial-dual-masked-autoencoder-for","slug":"intensity-spatial-dual-masked-autoencoder-for","title":"Intensity-Spatial Dual Masked Autoencoder for Multi-Scale Feature Learning in Chest CT Segmentation","date":"2024-11-20","arxiv_id":"2411.13198","n_code_links":1,"syntology":null},{"paper":null,"slug":"optical-flow-representation-alignment-mamba","title":"Optical Flow Representation Alignment Mamba Diffusion Model for Medical Video Generation","date":"2024-11-03","arxiv_id":"2411.01647","n_code_links":0,"syntology":null},{"paper":"/paper/cross-d-conv-cross-dimensional-transferable","slug":"cross-d-conv-cross-dimensional-transferable","title":"Cross-D Conv: Cross-Dimensional Transferable Knowledge Base via Fourier Shifting Operation","date":"2024-11-02","arxiv_id":"2411.02441","n_code_links":1,"syntology":null},{"paper":null,"slug":"preserving-cardiac-integrity-a-topology","title":"Preserving Cardiac Integrity: A Topology-Infused Approach to Whole Heart Segmentation","date":"2024-10-14","arxiv_id":"2410.10551","n_code_links":0,"syntology":null},{"paper":"/paper/reconstruction-of-particle-flow-energy","slug":"reconstruction-of-particle-flow-energy","title":"Lightweight Deep Learning Framework for Accurate Particle Flow Energy Reconstruction","date":"2024-10-08","arxiv_id":"2410.07250","n_code_links":1,"syntology":null},{"paper":null,"slug":"real-time-3d-occupancy-prediction-via","title":"Real-Time 3D Occupancy Prediction via Geometric-Semantic Disentanglement","date":"2024-07-18","arxiv_id":"2407.13155","n_code_links":0,"syntology":null},{"paper":"/paper/bidirectional-stereo-image-compression-with","slug":"bidirectional-stereo-image-compression-with","title":"Bidirectional Stereo Image Compression with Cross-Dimensional Entropy Model","date":"2024-07-15","arxiv_id":"2407.10632","n_code_links":1,"syntology":null},{"paper":null,"slug":"3d-adaptive-structural-convolution-network","title":"3D Adaptive Structural Convolution Network for Domain-Invariant Point Cloud Recognition","date":"2024-07-05","arxiv_id":"2407.04833","n_code_links":0,"syntology":null},{"paper":"/paper/arch2s-dataset-benchmark-and-challenges-for","slug":"arch2s-dataset-benchmark-and-challenges-for","title":"ARCH2S: Dataset, Benchmark and Challenges for Learning Exterior Architectural Structures from Point Clouds","date":"2024-06-03","arxiv_id":"2406.01337","n_code_links":1,"syntology":null},{"paper":"/paper/towards-automating-the-retrospective","slug":"towards-automating-the-retrospective","title":"Towards Automating the Retrospective Generation of BIM Models: A Unified Framework for 3D Semantic Reconstruction of the Built Environment","date":"2024-06-03","arxiv_id":"2406.01480","n_code_links":1,"syntology":null},{"paper":null,"slug":"ghost-stereo-ghostnet-based-cost-volume","title":"Ghost-Stereo: GhostNet-based Cost Volume Enhancement and Aggregation for Stereo Matching Networks","date":"2024-05-23","arxiv_id":"2405.14520","n_code_links":0,"syntology":null},{"paper":"/paper/lsk3dnet-towards-effective-and-efficient-3d","slug":"lsk3dnet-towards-effective-and-efficient-3d","title":"LSK3DNet: Towards Effective and Efficient 3D Perception with Large Sparse Kernels","date":"2024-03-22","arxiv_id":"2403.15173","n_code_links":1,"syntology":null},{"paper":"/paper/videomamba-state-space-model-for-efficient","slug":"videomamba-state-space-model-for-efficient","title":"VideoMamba: State Space Model for Efficient Video Understanding","date":"2024-03-11","arxiv_id":"2403.06977","n_code_links":2,"syntology":{"ran":9,"of":15,"n_ran_checked":6,"n_instrument":3,"unverified":6,"pointer_only":0,"phrase":"9 ran (of which 5 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 6 unverified","official":{"repos":["opengvlab/videomamba"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"med3dinsight-enhancing-3d-medical-image","title":"Med3DInsight: Enhancing 3D Medical Image Understanding with 2D Multi-Modal Large Language Models","date":"2024-03-08","arxiv_id":"2403.05141","n_code_links":0,"syntology":null},{"paper":null,"slug":"fastocc-accelerating-3d-occupancy-prediction","title":"FastOcc: Accelerating 3D Occupancy Prediction by Fusing the 2D Bird's-Eye View and Perspective View","date":"2024-03-05","arxiv_id":"2403.02710","n_code_links":0,"syntology":null},{"paper":null,"slug":"hybrid-video-diffusion-models-with-2d","title":"Hybrid Video Diffusion Models with 2D Triplane and 3D Wavelet Representation","date":"2024-02-21","arxiv_id":"2402.13729","n_code_links":0,"syntology":null},{"paper":"/paper/improving-robustness-for-joint-optimization","slug":"improving-robustness-for-joint-optimization","title":"Improving Robustness for Joint Optimization of Camera Poses and Decomposed Low-Rank Tensorial Radiance Fields","date":"2024-02-20","arxiv_id":"2402.13252","n_code_links":1,"syntology":null},{"paper":null,"slug":"hje-joint-convolutional-representation","title":"HJE: Joint Convolutional Representation Learning for Knowledge Hypergraph Completion","date":"2024-02-13","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"multiple-instance-learning-for-cheating","title":"Multiple Instance Learning for Cheating Detection and Localization in Online Examinations","date":"2024-02-09","arxiv_id":"2402.06107","n_code_links":0,"syntology":null},{"paper":"/paper/sage-icp-semantic-information-assisted-icp","slug":"sage-icp-semantic-information-assisted-icp","title":"SAGE-ICP: Semantic Information-Assisted ICP","date":"2023-10-11","arxiv_id":"2310.07237","n_code_links":1,"syntology":null},{"paper":"/paper/ndc-scene-boost-monocular-3d-semantic-scene","slug":"ndc-scene-boost-monocular-3d-semantic-scene","title":"NDC-Scene: Boost Monocular 3D Semantic Scene Completion in Normalized Device Coordinates Space","date":"2023-09-26","arxiv_id":"2309.14616","n_code_links":1,"syntology":{"ran":5,"of":7,"n_ran_checked":4,"n_instrument":1,"unverified":2,"pointer_only":7,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["Jiawei-Yao0812/NDCScene"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"a-dynamic-domain-adaptation-deep-learning","title":"A Dynamic Domain Adaptation Deep Learning Network for EEG-based Motor Imagery Classification","date":"2023-09-21","arxiv_id":"2309.11714","n_code_links":0,"syntology":null},{"paper":"/paper/multi-stage-factorized-spatio-temporal","slug":"multi-stage-factorized-spatio-temporal","title":"Multi-stage Factorized Spatio-Temporal Representation for RGB-D Action and Gesture Recognition","date":"2023-08-23","arxiv_id":"2308.12006","n_code_links":1,"syntology":null},{"paper":"/paper/fastllve-real-time-low-light-video","slug":"fastllve-real-time-low-light-video","title":"FastLLVE: Real-Time Low-Light Video Enhancement with Intensity-Aware Lookup Table","date":"2023-08-13","arxiv_id":"2308.06749","n_code_links":1,"syntology":null},{"paper":null,"slug":"raymvsnet-learning-ray-based-1d-implicit-1","title":"RayMVSNet++: Learning Ray-based 1D Implicit Fields for Accurate Multi-View Stereo","date":"2023-07-16","arxiv_id":"2307.10233","n_code_links":0,"syntology":null},{"paper":"/paper/spatial-spectral-hyperspectral-classification","slug":"spatial-spectral-hyperspectral-classification","title":"Spatial-Spectral Hyperspectral Classification based on Learnable 3D Group Convolution","date":"2023-07-15","arxiv_id":"2307.07720","n_code_links":1,"syntology":null},{"paper":"/paper/dgcnet-an-efficient-3d-densenet-based-on","slug":"dgcnet-an-efficient-3d-densenet-based-on","title":"DGCNet: An Efficient 3D-Densenet based on Dynamic Group Convolution for Hyperspectral Remote Sensing Image Classification","date":"2023-07-13","arxiv_id":"2307.06667","n_code_links":1,"syntology":null},{"paper":"/paper/general-purpose-multimodal-transformer-meets","slug":"general-purpose-multimodal-transformer-meets","title":"General-Purpose Multimodal Transformer meets Remote Sensing Semantic Segmentation","date":"2023-07-07","arxiv_id":"2307.03388","n_code_links":1,"syntology":null},{"paper":null,"slug":"toward-moire-free-and-detail-preserving","title":"Toward Moiré-Free and Detail-Preserving Demosaicking","date":"2023-05-15","arxiv_id":"2305.08585","n_code_links":0,"syntology":null},{"paper":null,"slug":"nearest-neighbor-inter-intra-contrastive","title":"Nearest-Neighbor Inter-Intra Contrastive Learning from Unlabeled Videos","date":"2023-03-13","arxiv_id":"2303.07317","n_code_links":0,"syntology":null},{"paper":null,"slug":"stpdnet-spatial-temporal-convolutional-primal","title":"STPDnet: Spatial-temporal convolutional primal dual network for dynamic PET image reconstruction","date":"2023-03-08","arxiv_id":"2303.04667","n_code_links":0,"syntology":null},{"paper":null,"slug":"a2s-nas-asymmetric-spectral-spatial-neural","title":"A2S-NAS: Asymmetric Spectral-Spatial Neural Architecture Search For Hyperspectral Image Classification","date":"2023-02-23","arxiv_id":"2302.11868","n_code_links":0,"syntology":null},{"paper":"/paper/lit-former-linking-in-plane-and-through-plane","slug":"lit-former-linking-in-plane-and-through-plane","title":"LIT-Former: Linking In-plane and Through-plane Transformers for Simultaneous CT Image Denoising and Deblurring","date":"2023-02-21","arxiv_id":"2302.10630","n_code_links":1,"syntology":null},{"paper":"/paper/adjacent-level-feature-cross-fusion-with-3d","slug":"adjacent-level-feature-cross-fusion-with-3d","title":"Adjacent-Level Feature Cross-Fusion With 3-D CNN for Remote Sensing Image Change Detection","date":"2023-02-10","arxiv_id":"2302.05109","n_code_links":1,"syntology":null},{"paper":null,"slug":"pdvn-a-patch-based-dual-view-network-for-face","title":"PDVN: A Patch-based Dual-view Network for Face Liveness Detection using Light Field Focal Stack","date":"2023-01-17","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/deep-diversity-enhanced-feature","slug":"deep-diversity-enhanced-feature","title":"Deep Diversity-Enhanced Feature Representation of Hyperspectral Images","date":"2023-01-15","arxiv_id":"2301.06132","n_code_links":1,"syntology":null},{"paper":null,"slug":"deep-learning-for-short-latency-epileptic","title":"Shorter Latency of Real-time Epileptic Seizure Detection via Probabilistic Prediction","date":"2023-01-04","arxiv_id":"2301.03465","n_code_links":0,"syntology":null},{"paper":null,"slug":"ddit-semantic-scene-completion-via-deformable","title":"DDIT: Semantic Scene Completion via Deformable Deep Implicit Templates","date":"2023-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"image-coupled-volume-propagation-for-stereo","title":"Image-Coupled Volume Propagation for Stereo Matching","date":"2022-12-30","arxiv_id":"2301.00695","n_code_links":0,"syntology":null},{"paper":"/paper/rainunet-for-super-resolution-rain-movie","slug":"rainunet-for-super-resolution-rain-movie","title":"RainUNet for Super-Resolution Rain Movie Prediction under Spatio-temporal Shifts","date":"2022-12-07","arxiv_id":"2212.04005","n_code_links":1,"syntology":{"ran":6,"of":8,"n_ran_checked":3,"n_instrument":3,"unverified":2,"pointer_only":0,"phrase":"6 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","official":{"repos":["jinyxp/weather4cast-2022"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"exploring-state-change-capture-of","title":"Exploring State Change Capture of Heterogeneous Backbones @ Ego4D Hands and Objects Challenge 2022","date":"2022-11-16","arxiv_id":"2211.08728","n_code_links":0,"syntology":null},{"paper":null,"slug":"combined-space-time-reduced-order-model-with","title":"Combined space-time reduced-order model with 3D deep convolution for extrapolating fluid dynamics","date":"2022-11-01","arxiv_id":"2211.00307","n_code_links":0,"syntology":null},{"paper":"/paper/real-time-monitoring-of-user-stress-heart","slug":"real-time-monitoring-of-user-stress-heart","title":"Real-Time Monitoring of User Stress, Heart Rate and Heart Rate Variability on Mobile Devices","date":"2022-10-04","arxiv_id":"2210.01791","n_code_links":0,"syntology":null},{"paper":"/paper/moving-from-2d-to-3d-volumetric-medical-image","slug":"moving-from-2d-to-3d-volumetric-medical-image","title":"Moving from 2D to 3D: volumetric medical image classification for rectal cancer staging","date":"2022-09-13","arxiv_id":"2209.05771","n_code_links":1,"syntology":null},{"paper":"/paper/ssfpn-scale-sequence-s-2-feature-based","slug":"ssfpn-scale-sequence-s-2-feature-based","title":"ssFPN: Scale Sequence (S^2) Feature Based-Feature Pyramid Network for Object Detection","date":"2022-08-24","arxiv_id":"2208.11533","n_code_links":4,"syntology":null},{"paper":"/paper/3d-vision-with-transformers-a-survey","slug":"3d-vision-with-transformers-a-survey","title":"3D Vision with Transformers: A Survey","date":"2022-08-08","arxiv_id":"2208.04309","n_code_links":1,"syntology":null},{"paper":null,"slug":"intelligent-3d-network-protocol-for","title":"Intelligent 3D Network Protocol for Multimedia Data Classification using Deep Learning","date":"2022-07-23","arxiv_id":"2207.11504","n_code_links":0,"syntology":null},{"paper":"/paper/splitmixer-fat-trimmed-from-mlp-like-models","slug":"splitmixer-fat-trimmed-from-mlp-like-models","title":"SplitMixer: Fat Trimmed From MLP-like Models","date":"2022-07-21","arxiv_id":"2207.10255","n_code_links":1,"syntology":null},{"paper":"/paper/federated-self-supervised-learning-for-video","slug":"federated-self-supervised-learning-for-video","title":"Federated Self-supervised Learning for Video Understanding","date":"2022-07-05","arxiv_id":"2207.01975","n_code_links":2,"syntology":null},{"paper":null,"slug":"wifi-based-spatiotemporal-human-action","title":"WiFi-based Spatiotemporal Human Action Perception","date":"2022-06-20","arxiv_id":"2206.09867","n_code_links":0,"syntology":null},{"paper":null,"slug":"2d-versus-3d-convolutional-spiking-neural","title":"2D versus 3D Convolutional Spiking Neural Networks Trained with Unsupervised STDP for Human Action Recognition","date":"2022-05-26","arxiv_id":"2205.13474","n_code_links":0,"syntology":null},{"paper":null,"slug":"scvrl-shuffled-contrastive-video","title":"SCVRL: Shuffled Contrastive Video Representation Learning","date":"2022-05-24","arxiv_id":"2205.11710","n_code_links":0,"syntology":null},{"paper":"/paper/pillarnet-high-performance-pillar-based-3d","slug":"pillarnet-high-performance-pillar-based-3d","title":"PillarNet: Real-Time and High-Performance Pillar-based 3D Object Detection","date":"2022-05-16","arxiv_id":"2205.07403","n_code_links":1,"syntology":null},{"paper":"/paper/in-defense-of-image-pre-training-for","slug":"in-defense-of-image-pre-training-for","title":"In Defense of Image Pre-Training for Spatiotemporal Recognition","date":"2022-05-03","arxiv_id":"2205.01721","n_code_links":1,"syntology":null},{"paper":"/paper/cpgnet-cascade-point-grid-fusion-network-for","slug":"cpgnet-cascade-point-grid-fusion-network-for","title":"CPGNet: Cascade Point-Grid Fusion Network for Real-Time LiDAR Semantic Segmentation","date":"2022-04-21","arxiv_id":"2204.09914","n_code_links":3,"syntology":{"ran":4,"of":4,"n_ran_checked":3,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["GangZhang842/CPGNet"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/global-and-local-collaborative-learning-for","slug":"global-and-local-collaborative-learning-for","title":"Global-and-Local Collaborative Learning for Co-Salient Object Detection","date":"2022-04-19","arxiv_id":"2204.08917","n_code_links":2,"syntology":null},{"paper":"/paper/feature-robustness-and-sex-differences-in","slug":"feature-robustness-and-sex-differences-in","title":"Feature robustness and sex differences in medical imaging: a case study in MRI-based Alzheimer's disease detection","date":"2022-04-04","arxiv_id":"2204.01737","n_code_links":1,"syntology":null},{"paper":null,"slug":"raymvsnet-learning-ray-based-1d-implicit","title":"RayMVSNet: Learning Ray-based 1D Implicit Fields for Accurate Multi-View Stereo","date":"2022-04-04","arxiv_id":"2204.01320","n_code_links":0,"syntology":null},{"paper":null,"slug":"transformer-based-video-front-ends-for-audio","title":"Transformer-Based Video Front-Ends for Audio-Visual Speech Recognition for Single and Multi-Person Video","date":"2022-01-25","arxiv_id":"2201.10439","n_code_links":0,"syntology":null},{"paper":null,"slug":"mutual-attention-based-hybrid-dimensional","title":"Mutual Attention-based Hybrid Dimensional Network for Multimodal Imaging Computer-aided Diagnosis","date":"2022-01-24","arxiv_id":"2201.09421","n_code_links":0,"syntology":null},{"paper":"/paper/uniformer-unified-transformer-for-efficient-1","slug":"uniformer-unified-transformer-for-efficient-1","title":"UniFormer: Unified Transformer for Efficient Spatiotemporal Representation Learning","date":"2022-01-12","arxiv_id":"2201.04676","n_code_links":2,"syntology":{"ran":27,"of":37,"n_ran_checked":16,"n_instrument":11,"unverified":10,"pointer_only":0,"phrase":"27 ran (of which 14 constructed an object rather than computing a result; 16 with no instrument failure: 1 honoured, 0 violated, 15 with no contract checked; 11 where Syntology's instrument failed) · 10 unverified","official":{"repos":["sense-x/uniformer"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"classification-of-hyperspectral-images-by","title":"Classification of Hyperspectral Images by Using Spectral Data and Fully Connected Neural Network","date":"2022-01-08","arxiv_id":"2201.02821","n_code_links":0,"syntology":null},{"paper":"/paper/not-all-voxels-are-equal-semantic-scene","slug":"not-all-voxels-are-equal-semantic-scene","title":"Not All Voxels Are Equal: Semantic Scene Completion from the Point-Voxel Perspective","date":"2021-12-24","arxiv_id":"2112.12925","n_code_links":0,"syntology":null},{"paper":"/paper/object-shape-error-response-using-bayesian-3","slug":"object-shape-error-response-using-bayesian-3","title":"Object Shape Error Response Using Bayesian 3-D Convolutional Neural Networks for Assembly Systems With Compliant Parts","date":"2021-12-08","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/staf-a-spatio-temporal-attention-fusion","slug":"staf-a-spatio-temporal-attention-fusion","title":"MASTAF: A Model-Agnostic Spatio-Temporal Attention Fusion Network for Few-shot Video Classification","date":"2021-12-08","arxiv_id":"2112.04585","n_code_links":1,"syntology":null},{"paper":null,"slug":"stsm-spatio-temporal-shift-module-for","title":"STSM: Spatio-Temporal Shift Module for Efficient Action Recognition","date":"2021-12-05","arxiv_id":"2112.02523","n_code_links":0,"syntology":null},{"paper":"/paper/roca-robust-cad-model-retrieval-and-alignment","slug":"roca-robust-cad-model-retrieval-and-alignment","title":"ROCA: Robust CAD Model Retrieval and Alignment from a Single Image","date":"2021-12-03","arxiv_id":"2112.01988","n_code_links":1,"syntology":null},{"paper":"/paper/traffic4cast-large-scale-traffic-prediction","slug":"traffic4cast-large-scale-traffic-prediction","title":"Traffic4cast -- Large-scale Traffic Prediction using 3DResNet and Sparse-UNet","date":"2021-11-10","arxiv_id":"2111.05990","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["resuly/traffic4cast-2021"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"sca-net-sparse-channel-attention-module-for","title":"SCA Net: Sparse Channel Attention Module for Action Recognition","date":"2021-10-15","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/uniformer-unified-transformer-for-efficient","slug":"uniformer-unified-transformer-for-efficient","title":"UniFormer: Unified Transformer for Efficient Spatial-Temporal Representation Learning","date":"2021-09-29","arxiv_id":null,"n_code_links":3,"syntology":null},{"paper":"/paper/cylindrical-and-asymmetrical-3d-convolution-1","slug":"cylindrical-and-asymmetrical-3d-convolution-1","title":"Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR-based Perception","date":"2021-09-12","arxiv_id":"2109.05441","n_code_links":1,"syntology":{"ran":6,"of":7,"n_ran_checked":3,"n_instrument":3,"unverified":1,"pointer_only":2,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","official":{"repos":["xinge008/Cylinder3D"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/revisiting-3d-resnets-for-video-recognition","slug":"revisiting-3d-resnets-for-video-recognition","title":"Revisiting 3D ResNets for Video Recognition","date":"2021-09-03","arxiv_id":"2109.01696","n_code_links":5,"syntology":null},{"paper":null,"slug":"simullr-simultaneous-lip-reading-transducer","title":"SimulLR: Simultaneous Lip Reading Transducer with Attention-Guided Adaptive Memory","date":"2021-08-31","arxiv_id":"2108.13630","n_code_links":0,"syntology":null},{"paper":"/paper/ligar-lightweight-general-purpose-action","slug":"ligar-lightweight-general-purpose-action","title":"LIGAR: Lightweight General-purpose Action Recognition","date":"2021-08-30","arxiv_id":"2108.13153","n_code_links":1,"syntology":null},{"paper":"/paper/spatio-temporal-self-attention-network-for","slug":"spatio-temporal-self-attention-network-for","title":"Spatio-Temporal Self-Attention Network for Video Saliency Prediction","date":"2021-08-24","arxiv_id":"2108.10696","n_code_links":1,"syntology":null},{"paper":null,"slug":"volumefusion-deep-depth-fusion-for-3d-scene","title":"VolumeFusion: Deep Depth Fusion for 3D Scene Reconstruction","date":"2021-08-19","arxiv_id":"2108.08623","n_code_links":0,"syntology":null},{"paper":"/paper/interpolation-aware-padding-for-3d-sparse","slug":"interpolation-aware-padding-for-3d-sparse","title":"Interpolation-Aware Padding for 3D Sparse Convolutional Neural Networks","date":"2021-08-16","arxiv_id":"2108.06925","n_code_links":1,"syntology":null},{"paper":"/paper/cnn-based-autoencoder-application-in-breast","slug":"cnn-based-autoencoder-application-in-breast","title":"CNN Based Autoencoder Application in Breast Cancer Image Retrieval","date":"2021-08-04","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/self-supervised-video-representation-learning-7","slug":"self-supervised-video-representation-learning-7","title":"Self-supervised Video Representation Learning with Cross-Stream Prototypical Contrasting","date":"2021-06-18","arxiv_id":"2106.10137","n_code_links":1,"syntology":null},{"paper":null,"slug":"3d-convolution-neural-network-based-person","title":"3D Convolution Neural Network based Person Identification using Gait cycles","date":"2021-06-06","arxiv_id":"2106.03136","n_code_links":0,"syntology":null},{"paper":null,"slug":"r2u3d-recurrent-residual-3d-u-net-for-lung","title":"R2U3D: Recurrent Residual 3D U-Net for Lung Segmentation","date":"2021-05-05","arxiv_id":"2105.02290","n_code_links":0,"syntology":null},{"paper":"/paper/convolutional-neural-networks-for-alzheimers","slug":"convolutional-neural-networks-for-alzheimers","title":"Convolutional neural networks for Alzheimer’s disease detection on MRI images","date":"2021-04-29","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/mvs2d-efficient-multi-view-stereo-via","slug":"mvs2d-efficient-multi-view-stereo-via","title":"MVS2D: Efficient Multi-view Stereo via Attention-Driven 2D Convolutions","date":"2021-04-27","arxiv_id":"2104.13325","n_code_links":1,"syntology":{"ran":8,"of":9,"n_ran_checked":7,"n_instrument":1,"unverified":1,"pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["zhenpeiyang/MVS2D"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"bevdetnet-bird-s-eye-view-lidar-point-cloud","title":"BEVDetNet: Bird's Eye View LiDAR Point Cloud based Real-time 3D Object Detection for Autonomous Driving","date":"2021-04-21","arxiv_id":"2104.10780","n_code_links":0,"syntology":null},{"paper":"/paper/vr3dense-voxel-representation-learning-for-3d","slug":"vr3dense-voxel-representation-learning-for-3d","title":"VR3Dense: Voxel Representation Learning for 3D Object Detection and Monocular Dense Depth Reconstruction","date":"2021-04-13","arxiv_id":"2104.05932","n_code_links":1,"syntology":null},{"paper":"/paper/dogfight-detecting-drones-from-drones-videos","slug":"dogfight-detecting-drones-from-drones-videos","title":"Dogfight: Detecting Drones from Drones Videos","date":"2021-03-31","arxiv_id":"2103.17242","n_code_links":2,"syntology":null},{"paper":"/paper/an-image-is-worth-16x16-words-what-is-a-video","slug":"an-image-is-worth-16x16-words-what-is-a-video","title":"An Image is Worth 16x16 Words, What is a Video Worth?","date":"2021-03-25","arxiv_id":"2103.13915","n_code_links":2,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":{"repos":["Alibaba-MIIL/STAM"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":null,"slug":"large-motion-video-super-resolution-with-dual","title":"Large Motion Video Super-Resolution with Dual Subnet and Multi-Stage Communicated Upsampling","date":"2021-03-22","arxiv_id":"2103.11744","n_code_links":0,"syntology":null},{"paper":null,"slug":"nas-tc-neural-architecture-search-on-temporal","title":"NAS-TC: Neural Architecture Search on Temporal Convolutions for Complex Action Recognition","date":"2021-03-17","arxiv_id":"2104.01110","n_code_links":0,"syntology":null},{"paper":"/paper/skeleton-based-sign-language-recognition","slug":"skeleton-based-sign-language-recognition","title":"Skeleton Aware Multi-modal Sign Language Recognition","date":"2021-03-16","arxiv_id":"2103.08833","n_code_links":3,"syntology":null},{"paper":"/paper/action-net-multipath-excitation-for-action","slug":"action-net-multipath-excitation-for-action","title":"ACTION-Net: Multipath Excitation for Action Recognition","date":"2021-03-11","arxiv_id":"2103.07372","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","official":{"repos":["V-Sense/ACTION-Net"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"touchless-palmprint-recognition-based-on-3d","title":"Touchless Palmprint Recognition based on 3D Gabor Template and Block Feature Refinement","date":"2021-03-03","arxiv_id":"2103.02167","n_code_links":0,"syntology":null}],"papers_shown":100,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":208,"with_a_code_link":107,"where_syntology_ran_a_sample":20,"not_listed_spam_title":0,"listed":208,"listed_where_code_ran":20,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":18,"every_run_a_failure_of_syntologys_instrument":2,"listed_with_a_run_with_no_instrument_failure":18,"listed_every_run_a_failure_of_syntologys_instrument":2,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"papers_where_code_ran":20,"papers_where_code_ran_first_page":"/method/3d-convolution/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not isolate this method inside it.","pages":[{"order":"archive","page":2,"of":3,"url":"/method/3d-convolution/papers/2","json":"/method/3d-convolution/papers/2.json","rows":100},{"order":"archive","page":3,"of":3,"url":"/method/3d-convolution/papers/3","json":"/method/3d-convolution/papers/3.json","rows":8},{"order":"ran","page":1,"of":1,"url":"/method/3d-convolution/papers/ran/1","json":"/method/3d-convolution/papers/ran/1.json","rows":20}],"tasks":[{"task":"/task/action-recognition-in-videos","name":"Action Recognition","papers":30},{"task":"/task/semantic-segmentation","name":"Semantic Segmentation","papers":21},{"task":"/task/segmentation","name":"Segmentation","papers":15},{"task":"/task/action-recognition","name":"Temporal Action Localization","papers":15},{"task":"/task/object-detection","name":"Object Detection","papers":14},{"task":"/task/object-detection-1","name":"object-detection","papers":13},{"task":"/task/image-classification","name":"Image Classification","papers":12},{"task":"/task/image-classification","name":"image-classification","papers":12},{"task":"/task/autonomous-driving","name":"Autonomous Driving","papers":10},{"task":"/task/deep-learning","name":"Deep Learning","papers":9},{"task":"/task/representation-learning","name":"Representation Learning","papers":9},{"task":"/task/super-resolution","name":"Super-Resolution","papers":9},{"task":"/task/depth-estimation","name":"Depth Estimation","papers":8},{"task":"/task/3d-semantic-segmentation","name":"3D Semantic Segmentation","papers":7},{"task":"/task/decoder","name":"Decoder","papers":7},{"task":"/task/denoising","name":"Denoising","papers":7},{"task":"/task/stereo-matching-1","name":"Stereo Matching","papers":7},{"task":"/task/video-understanding","name":"Video Understanding","papers":7},{"task":"/task/3d-object-detection","name":"3D Object Detection","papers":6},{"task":"/task/contrastive-learning","name":"Contrastive Learning","papers":6}],"tasks_shown":20,"n_tasks":263,"usage_by_year":[{"year":"1994","papers":1},{"year":"2015","papers":2},{"year":"2016","papers":3},{"year":"2017","papers":8},{"year":"2018","papers":18},{"year":"2019","papers":34},{"year":"2020","papers":39},{"year":"2021","papers":33},{"year":"2022","papers":24},{"year":"2023","papers":19},{"year":"2024","papers":21},{"year":"2025","papers":6}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/3d-convolution"},"syntology_read_at":"2026-10-05T00:36:11+00:00","syntology":{"source":"Syntology's have check for this name (the free coverage lookup), read from Syntology's graph","have_url":"https://syntology.ai/api/graph/have?x=3D%20Convolution","read_at":"2026-10-05T00:51:12+00:00","query":"3D Convolution","kind":"method","have":"unknown_name","tier":null,"verified_implementation":null,"level":null,"level_meaning":"the served verification level, per answer; never summed across methods","resolved_to":null,"resolution":null,"resolved_name_differs":false,"absence_asserted":false,"absence_unchecked":null,"no_code_is_about_this_method":false,"subject":null,"archive_paper_arxiv_id":null,"repositories":null,"retrieve_with":null,"name_competition":{"verdict":"none","may_be_wrong_sense":false,"bearers_found":0,"served":null,"leading_other_bearer":null,"n_other_bearers_listed":0,"note":"Nothing in this corpus is named '3D Convolution' -- no method node, no paper announcing it in its title, no expanded form declaring it as an acronym."},"name_competition_text":null,"near_matches":["3D convolutional neural network model","3D Convolution-Transformer Mixture (CTM) module","Encoding Clinical Priori in 3D Convolutional Neural Networks","Convolutional Surrogate for 3D Discrete Fracture-Matrix Tensor Upscaling","encoder-decoder network with 3D convolutional neural networks and visual saliency","X-3D"],"code_nearby":[],"code_nearby_caption":null,"origin_paper":null,"line":"name not resolved (unknown_name). The lookup matched no method, paper or venue by this name; that asserts nothing about whether code exists.","level_legend":null},"syntology_have_state":"loaded","record_sha256":"339b6375017a13f93618089c077e93796e88a15eb73adb269396ddc51614b445","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}