{"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/attention-pooling","slug":"attention-pooling","name":"Attention Pooling","full_name":"Attention Pooling","full_name_withheld":false,"description_markdown":null,"description_state":"absent","introduced_year":null,"introduced_by":{"title":"Network Level Spatial Temporal Traffic State Forecasting with Hierarchical Attention LSTM (HierAttnLSTM)","paper":"/paper/big-data-application-for-network-level-travel","first_author":"Tianya Terry Zhang","n_authors":1,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/big-data-application-for-network-level-travel"},"source":{"url":"https://arxiv.org/abs/2201.05760v4","title":"Network Level Spatial Temporal Traffic State Forecasting with Hierarchical Attention LSTM (HierAttnLSTM)","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"Feature Pyramid Blocks","url":"/methods/category/feature-pyramid-blocks","pwc_aliases":[]}],"n_papers_tagged":46,"archive_num_papers":46,"papers_newest_first":[{"paper":null,"slug":"frequency-dynamic-convolutions-for-sound","title":"Frequency Dynamic Convolutions for Sound Event Detection","date":"2025-06-15","arxiv_id":"2506.12785","n_code_links":0,"syntology":null},{"paper":null,"slug":"biolangfusion-multimodal-fusion-of-dna-mrna","title":"BioLangFusion: Multimodal Fusion of DNA, mRNA, and Protein Language Models","date":"2025-06-10","arxiv_id":"2506.08936","n_code_links":0,"syntology":null},{"paper":"/paper/using-diffusion-ensembles-to-estimate","slug":"using-diffusion-ensembles-to-estimate","title":"Using Diffusion Ensembles to Estimate Uncertainty for End-to-End Autonomous Driving","date":"2025-05-31","arxiv_id":"2506.00560","n_code_links":0,"syntology":null},{"paper":null,"slug":"triple-attention-transformer-architecture-for","title":"Triple Attention Transformer Architecture for Time-Dependent Concrete Creep Prediction","date":"2025-05-28","arxiv_id":"2506.04243","n_code_links":0,"syntology":null},{"paper":null,"slug":"setransformer-a-hybrid-attention-based","title":"SETransformer: A Hybrid Attention-Based Architecture for Robust Human Activity Recognition","date":"2025-05-25","arxiv_id":"2505.19369","n_code_links":0,"syntology":null},{"paper":null,"slug":"beyond-node-attention-multi-scale-harmonic","title":"Beyond Node Attention: Multi-Scale Harmonic Encoding for Feature-Wise Graph Message Passing","date":"2025-05-21","arxiv_id":"2505.15015","n_code_links":0,"syntology":null},{"paper":"/paper/recdap-relation-based-conditional-diffusion","slug":"recdap-relation-based-conditional-diffusion","title":"ReCDAP: Relation-Based Conditional Diffusion with Attention Pooling for Few-Shot Knowledge Graph Completion","date":"2025-05-12","arxiv_id":"2505.07171","n_code_links":1,"syntology":null},{"paper":"/paper/efficient-document-retrieval-with-g-retriever","slug":"efficient-document-retrieval-with-g-retriever","title":"Efficient Document Retrieval with G-Retriever","date":"2025-04-21","arxiv_id":"2504.14955","n_code_links":1,"syntology":null},{"paper":"/paper/temporal-attention-pooling-for-frequency","slug":"temporal-attention-pooling-for-frequency","title":"Temporal Attention Pooling for Frequency Dynamic Convolution in Sound Event Detection","date":"2025-04-17","arxiv_id":"2504.12670","n_code_links":1,"syntology":null},{"paper":"/paper/biox-cpath-biologically-driven-explainable","slug":"biox-cpath-biologically-driven-explainable","title":"BioX-CPath: Biologically-driven Explainable Diagnostics for Multistain IHC Computational Pathology","date":"2025-03-26","arxiv_id":"2503.20880","n_code_links":1,"syntology":null},{"paper":null,"slug":"llava-mlb-mitigating-and-leveraging-attention","title":"LLaVA-MLB: Mitigating and Leveraging Attention Bias for Training-Free Video LLMs","date":"2025-03-14","arxiv_id":"2503.11205","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-comprehensive-framework-for-semantic","title":"A Comprehensive Framework for Semantic Similarity Analysis of Human and AI-Generated Text Using Transformer Architectures and Ensemble Techniques","date":"2025-01-24","arxiv_id":"2501.14288","n_code_links":0,"syntology":null},{"paper":"/paper/flair-vlm-with-fine-grained-language-informed","slug":"flair-vlm-with-fine-grained-language-informed","title":"FLAIR: VLM with Fine-grained Language-informed Image Representations","date":"2024-12-04","arxiv_id":"2412.03561","n_code_links":2,"syntology":{"ran":13,"of":20,"n_ran_checked":4,"n_instrument":9,"unverified":7,"pointer_only":20,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 1 violated, 1 with no contract checked; 9 where Syntology's instrument failed) · 7 unverified","official":{"repos":["explainableml/flair"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"infantcrynet-a-data-driven-framework-for","title":"InfantCryNet: A Data-driven Framework for Intelligent Analysis of Infant Cries","date":"2024-09-29","arxiv_id":"2409.19689","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficiently-expanding-receptive-fields-local","title":"Efficiently Expanding Receptive Fields: Local Split Attention and Parallel Aggregation for Enhanced Large-scale Point Cloud Semantic Segmentation","date":"2024-09-03","arxiv_id":"2409.01662","n_code_links":0,"syntology":null},{"paper":"/paper/bsc-upc-at-emospeech-iberlef2024-attention","slug":"bsc-upc-at-emospeech-iberlef2024-attention","title":"BSC-UPC at EmoSPeech-IberLEF2024: Attention Pooling for Emotion Recognition","date":"2024-07-17","arxiv_id":"2407.12467","n_code_links":1,"syntology":null},{"paper":"/paper/auto-vocabulary-segmentation-for-lidar-points","slug":"auto-vocabulary-segmentation-for-lidar-points","title":"3D-AVS: LiDAR-based 3D Auto-Vocabulary Segmentation","date":"2024-06-13","arxiv_id":"2406.09126","n_code_links":1,"syntology":null},{"paper":null,"slug":"transformer-based-self-supervised-learning-1","title":"Transformer-Based Self-Supervised Learning for Histopathological Classification of Ischemic Stroke Clot Origin","date":"2024-05-01","arxiv_id":"2405.00908","n_code_links":0,"syntology":null},{"paper":"/paper/ki-gan-knowledge-informed-generative","slug":"ki-gan-knowledge-informed-generative","title":"KI-GAN: Knowledge-Informed Generative Adversarial Networks for Enhanced Multi-Vehicle Trajectory Forecasting at Signalized Intersections","date":"2024-04-17","arxiv_id":"2404.11181","n_code_links":1,"syntology":null},{"paper":null,"slug":"pathology-genomic-fusion-via-biologically","title":"Pathology-genomic fusion via biologically informed cross-modality graph learning for survival analysis","date":"2024-04-11","arxiv_id":"2404.08023","n_code_links":0,"syntology":null},{"paper":null,"slug":"advancing-graph-neural-networks-with-hl-hgat","title":"Advancing Graph Neural Networks with HL-HGAT: A Hodge-Laplacian and Attention Mechanism Approach for Heterogeneous Graph-Structured Data","date":"2024-03-11","arxiv_id":"2403.06687","n_code_links":0,"syntology":null},{"paper":"/paper/masked-attention-is-all-you-need-for-graphs","slug":"masked-attention-is-all-you-need-for-graphs","title":"An end-to-end attention-based approach for learning on graphs","date":"2024-02-16","arxiv_id":"2402.10793","n_code_links":1,"syntology":null},{"paper":null,"slug":"ttmfn-two-stream-transformer-based-multimodal","title":"TTMFN: Two-stream Transformer-based Multimodal Fusion Network for Survival Prediction","date":"2023-11-13","arxiv_id":"2311.07033","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-few-shot-clip-with-semantic-aware","title":"Enhancing Few-shot CLIP with Semantic-Aware Fine-Tuning","date":"2023-11-08","arxiv_id":"2311.04464","n_code_links":0,"syntology":null},{"paper":"/paper/reference-based-restoration-of-digitized","slug":"reference-based-restoration-of-digitized","title":"Reference-based Restoration of Digitized Analog Videotapes","date":"2023-10-20","arxiv_id":"2310.14926","n_code_links":2,"syntology":null},{"paper":null,"slug":"a-new-multimodal-medical-image-fusion-based","title":"A New Multimodal Medical Image Fusion based on Laplacian Autoencoder with Channel Attention","date":"2023-10-18","arxiv_id":"2310.11896","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-modal-medical-neurological-image-fusion","title":"Multi-modal Medical Neurological Image Fusion using Wavelet Pooled Edge Preserving Autoencoder","date":"2023-10-18","arxiv_id":"2310.11910","n_code_links":0,"syntology":null},{"paper":"/paper/rethinking-transfer-and-auxiliary-learning","slug":"rethinking-transfer-and-auxiliary-learning","title":"Rethinking Transfer and Auxiliary Learning for Improving Audio Captioning Transformer","date":"2023-08-20","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/explainable-2d-vision-models-for-3d-medical","slug":"explainable-2d-vision-models-for-3d-medical","title":"Interpretable 2D Vision Models for 3D Medical Images","date":"2023-07-13","arxiv_id":"2307.06614","n_code_links":1,"syntology":null},{"paper":null,"slug":"towards-effective-and-compact-contextual","title":"Towards Effective and Compact Contextual Representation for Conformer Transducer Speech Recognition Systems","date":"2023-06-23","arxiv_id":"2306.13307","n_code_links":0,"syntology":null},{"paper":"/paper/a-hierarchical-context-aware-modeling","slug":"a-hierarchical-context-aware-modeling","title":"A Hierarchical Context-aware Modeling Approach for Multi-aspect and Multi-granular Pronunciation Assessment","date":"2023-05-29","arxiv_id":"2305.18146","n_code_links":0,"syntology":null},{"paper":"/paper/ditto-a-simple-and-efficient-approach-to","slug":"ditto-a-simple-and-efficient-approach-to","title":"Ditto: A Simple and Efficient Approach to Improve Sentence Embeddings","date":"2023-05-18","arxiv_id":"2305.10786","n_code_links":1,"syntology":null},{"paper":"/paper/pixel-level-explanation-of-multiple-instance","slug":"pixel-level-explanation-of-multiple-instance","title":"Pixel-Level Explanation of Multiple Instance Learning Models in Biomedical Single Cell Images","date":"2023-03-15","arxiv_id":"2303.08632","n_code_links":1,"syntology":null},{"paper":"/paper/decompl-decompositional-learning-with","slug":"decompl-decompositional-learning-with","title":"DECOMPL: Decompositional Learning with Attention Pooling for Group Activity Recognition from a Single Volleyball Image","date":"2023-03-11","arxiv_id":"2303.06439","n_code_links":1,"syntology":null},{"paper":"/paper/the-impact-of-subword-pooling-strategy-for","slug":"the-impact-of-subword-pooling-strategy-for","title":"Impact of Subword Pooling Strategy on Cross-lingual Event Detection","date":"2023-02-22","arxiv_id":"2302.11365","n_code_links":1,"syntology":null},{"paper":"/paper/dont-judge-a-language-model-by-its-last-layer","slug":"dont-judge-a-language-model-by-its-last-layer","title":"Don’t Judge a Language Model by Its Last Layer: Contrastive Learning with Layer-Wise Attention Pooling","date":"2022-10-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/pre-trained-speech-representations-as-feature","slug":"pre-trained-speech-representations-as-feature","title":"Pre-trained Speech Representations as Feature Extractors for Speech Quality Assessment in Online Conferencing Applications","date":"2022-10-01","arxiv_id":"2210.00259","n_code_links":1,"syntology":null},{"paper":"/paper/exploring-visual-interpretability-for","slug":"exploring-visual-interpretability-for","title":"Exploring Visual Interpretability for Contrastive Language-Image Pre-training","date":"2022-09-15","arxiv_id":"2209.07046","n_code_links":1,"syntology":null},{"paper":"/paper/don-t-judge-a-language-model-by-its-last","slug":"don-t-judge-a-language-model-by-its-last","title":"Don't Judge a Language Model by Its Last Layer: Contrastive Learning with Layer-Wise Attention Pooling","date":"2022-09-13","arxiv_id":"2209.05972","n_code_links":1,"syntology":null},{"paper":null,"slug":"efficient-dynamic-filter-for-robust-and-low","title":"Efficient dynamic filter for robust and low computational feature extraction","date":"2022-05-03","arxiv_id":"2205.01304","n_code_links":0,"syntology":null},{"paper":"/paper/encoding-cardiopulmonary-exercise-testing","slug":"encoding-cardiopulmonary-exercise-testing","title":"Encoding Cardiopulmonary Exercise Testing Time Series as Images for Classification using Convolutional Neural Network","date":"2022-04-26","arxiv_id":"2204.12432","n_code_links":1,"syntology":null},{"paper":null,"slug":"audio-deep-fake-detection-system-with-neural","title":"Audio Deep Fake Detection System with Neural Stitching for ADD 2022","date":"2022-04-19","arxiv_id":"2204.08720","n_code_links":0,"syntology":null},{"paper":"/paper/large-scale-streaming-end-to-end-speech","slug":"large-scale-streaming-end-to-end-speech","title":"Large-Scale Streaming End-to-End Speech Translation with Neural Transducers","date":"2022-04-11","arxiv_id":"2204.05352","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/compositionality-aware-graph2seq-learning","slug":"compositionality-aware-graph2seq-learning","title":"Compositionality-Aware Graph2Seq Learning","date":"2022-01-28","arxiv_id":"2201.12178","n_code_links":1,"syntology":null},{"paper":null,"slug":"lap-an-attention-based-module-for-faithful","title":"LAP: An Attention-Based Module for Concept Based Self-Interpretation and Knowledge Injection in Convolutional Neural Networks","date":"2022-01-27","arxiv_id":"2201.11808","n_code_links":0,"syntology":null},{"paper":"/paper/big-data-application-for-network-level-travel","slug":"big-data-application-for-network-level-travel","title":"Network Level Spatial Temporal Traffic State Forecasting with Hierarchical Attention LSTM (HierAttnLSTM)","date":"2022-01-15","arxiv_id":"2201.05760","n_code_links":1,"syntology":null}],"papers_shown":46,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":46,"with_a_code_link":23,"where_syntology_ran_a_sample":2,"not_listed_spam_title":0,"listed":46,"listed_where_code_ran":2,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":2,"listed_every_run_a_failure_of_syntologys_instrument":0,"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":2,"papers_where_code_ran_first_page":"/method/attention-pooling/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":"ran","page":1,"of":1,"url":"/method/attention-pooling/papers/ran/1","json":"/method/attention-pooling/papers/ran/1.json","rows":2}],"tasks":[{"task":"/task/semantic-textual-similarity","name":"Semantic Textual Similarity","papers":5},{"task":"/task/diagnostic","name":"Diagnostic","papers":4},{"task":"/task/language-modeling","name":"Language Modeling","papers":4},{"task":"/task/language-modelling","name":"Language Modelling","papers":4},{"task":"/task/retrieval","name":"Retrieval","papers":4},{"task":"/task/sentence","name":"Sentence","papers":4},{"task":"/task/autonomous-driving","name":"Autonomous Driving","papers":3},{"task":"/task/event-detection","name":"Event Detection","papers":3},{"task":"/task/graph-neural-network","name":"Graph Neural Network","papers":3},{"task":"/task/sts","name":"STS","papers":3},{"task":"/task/transfer-learning","name":"Transfer Learning","papers":3},{"task":"/task/activity-recognition","name":"Activity Recognition","papers":2},{"task":"/task/automatic-speech-recognition-2","name":"Automatic Speech Recognition","papers":2},{"task":"/task/contrastive-learning","name":"Contrastive Learning","papers":2},{"task":"/task/decision-making","name":"Decision Making","papers":2},{"task":"/task/graph-regression","name":"Graph Regression","papers":2},{"task":"/task/molecular-property-prediction","name":"Molecular Property Prediction","papers":2},{"task":"/task/multiple-instance-learning","name":"Multiple Instance Learning","papers":2},{"task":"/task/node-classification","name":"Node Classification","papers":2},{"task":"/task/prediction","name":"Prediction","papers":2}],"tasks_shown":20,"n_tasks":108,"usage_by_year":[{"year":"2022","papers":11},{"year":"2023","papers":13},{"year":"2024","papers":10},{"year":"2025","papers":12}],"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/attention-pooling"},"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=Attention%20Pooling","read_at":"2026-10-05T00:52:47+00:00","query":"Attention Pooling","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":"2201.05760","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 'Attention Pooling' -- no method node, no paper announcing it in its title, no expanded form declaring it as an acronym."},"name_competition_text":null,"near_matches":["active-frame QKV attention pooling","Attention Sliced Wasserstein Pooling","Context-aware Attentional Pooling (CAP)","Coarsened Graph Attention Pooling (CGAP)","Region Self-attention with Spatial Pyramid Pooling (RSSPP)","QKV Pooling","GMM Pooling","EL-Attention"],"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":"d34b7421022d2c7accd79bb44c24542cb1af4bf16ad4017bce2b6559320cdd75","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}