Browse State-of-the-Art › Scene Recognition
Scene Recognition
68 papers with code · 8 benchmarks · 16 datasets archive 2025-07-28
Benchmarks archive 2025-07-28
8 leaderboard tables shown for this task, 8 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.
Syntology 2 newer papers were judged to report on this task's benchmarks so far (Claude Sonnet 4.5, reading their tables: a model's judgement, not a result; 0 placed): AID (1 judged, 0 placed), SUN-RGBD (1 judged, 0 placed). Drawn from 8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read).
Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
Libraries
Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.
Datasets archive 2025-07-28
16 datasets whose archive record lists this task, ordered by the archive's paper count.
Subtasks archive 2025-07-28
No subtask under this task in the archive's task tree.
Parent tasks archive 2025-07-28
Papers archive 2025-07-28
archive papers tagged: 207 · with a code link: 68 · where Syntology ran a sample: 8 (7 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (8 of 207 tagged: 7 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument)
Page 1 of 3: papers 1 to 100 of 207, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.
Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.
-
27 Feb 2018 11 repositories listed Syntology 13 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 3 honoured, 1 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified (of 15 harvested samples) · 6 pointer-only (licence)We demonstrate CSRNet on four datasets (ShanghaiTech dataset, the UCF_CC_50 dataset, the WorldEXPO'10 dataset, and the UCSD dataset) and we deliver the state-of-the-art performance.
-
6 Oct 2013 8 repositories listed Syntology 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified (of 7 harvested samples) · 1 pointer-only (licence)We evaluate whether features extracted from the activation of a deep convolutional network trained in a fully supervised fashion on a large, fixed set of object recognition tasks can be re-purposed to novel generic…
-
29 Apr 2015 4 repositories listedWe then present a systematic analysis of these networks and show that (1) the bilinear features are highly redundant and can be reduced by an order of magnitude in size without significant loss in accuracy, (2) are also…
-
23 Mar 2014 4 repositories listedWe report on a series of experiments conducted for different recognition tasks using the publicly available code and model of the \overfeat network which was trained to perform object classification on ILSVRC13.
-
18 May 2020 3 repositories listedIn this paper, we explore the problem of interesting scene prediction for mobile robots.
-
6 Apr 2022 2 repositories listedTo this end, we train different networks from scratch with the help of the largest RS scene recognition dataset up to now -- MillionAID, to obtain a series of RS pretrained backbones, including both convolutional neural…
-
20 Jan 2022 2 repositories listed Syntology official (archive's flag): 1 ran · 2 ran (of which 2 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; every one of the 2 samples that ran constructed an object rather than computing a result (of 2 harvested samples) · 1 pointer-only (licence)Prior work has studied different visual modalities in isolation and developed separate architectures for recognition of images, videos, and 3D data.
-
31 Aug 2020 2 repositories listed Syntology official (archive's flag): 3 ran · 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 3 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 5 harvested samples) · 3 pointer-only (licence)Specifically, given an unlabeled video clip, we compute a series of spatio-temporal statistical summaries, such as the spatial location and dominant direction of the largest motion, the spatial location and dominant…
-
28 Feb 2020 2 repositories listedMoreover, we advocate multi-task learning as a way of improving scene recognition, building on the fact that the scene type is highly correlated with the objects in the scene, and therefore with its semantic…
-
10 Dec 2019 2 repositories listedThe hallucination task is treated as an auxiliary task, which can be used with any other action related task in a multitask learning setting.
-
3 Jan 2019 2 repositories listedSupervised machine learning based state-of-the-art computer vision techniques are in general data hungry.
-
4 Oct 2016 2 repositories listedConvolutional Neural Networks (CNNs) have made remarkable progress on scene recognition, partially due to these recent large-scale scene datasets, such as the Places and Places2.
-
7 Aug 2015 2 repositories listedWe verify the performance of trained Places205-VGGNet models on three datasets: MIT67, SUN397, and Places205.
-
9 Jan 2025 1 repository listedIn this study, we address this gap by constructing a large-scale ALS point cloud dataset and evaluating its impact on downstream applications.
-
1 Jan 2025 1 repository listedHowever, existing visual-to-visual and visual-to-textual Ego-Exo video alignment methods struggle with the problem that there could be non-visual overlap for the same activity.
-
4 Oct 2024 1 repository listed Syntology official (archive's flag): 5 ran · 5 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; 5 where Syntology's instrument failed) · 4 unverified (of 9 harvested samples) · 9 pointer-only (licence)To address this issue, we impose a requirement on learning systems to ensure that a new model strictly retains important capabilities of the old model while improving target-task performance, which we term model…
-
16 May 2024 1 repository listedContinuing with the above, we propose PIR-CLIP, a domain-specific CLIP-based framework for remote sensing image-text retrieval, to address semantic noise in remote sensing vision-language representations and further…
-
11 Dec 2023 1 repository listedVisual Question Answering (VQA) is one of the most important tasks in autonomous driving, which requires accurate recognition and complex situation evaluations.
-
9 Nov 2023 1 repository listedThis has been a significant bottleneck, particularly in the development of common sense reasoning and nuanced scene understanding necessary for safe and reliable autonomous driving.
-
4 Nov 2023 1 repository listedIn this paper, we propose a deep learning based crowd counting approach to automatically count number of manatees within a region, by using low quality images as input.
-
27 Oct 2023 1 repository listedOur highlight is the proposal of a paradigm that draws on prior knowledge to instruct adaptive learning of vision and text representations.
-
16 Jun 2023 1 repository listedIt consists of two stages, space granulation and attribute granulation.
-
23 May 2023 1 repository listedWe show that our questions 1) adequately represent the source material 2) can be used to diagnose a model's memory capacity 3) are not trivial for modern language models even when the memory demand does not exceed those…
-
15 May 2023 1 repository listedDespite the remarkable success of convolutional neural networks in various computer vision tasks, recognizing indoor scenes still presents a significant challenge due to their complex composition.
-
13 Mar 2023 1 repository listedMost deep learning backbones are evaluated on ImageNet.
-
13 Feb 2023 1 repository listedOur CoMAE presents a curriculum learning strategy to unify the two popular self-supervised representation learning algorithms: contrastive learning and masked image modeling.
-
15 Nov 2022 1 repository listed Syntology official: harvested, nothing ran · 0 ran · 1 unverified (of 1 harvested sample)A shared goal of several machine learning communities like continual learning, meta-learning and transfer learning, is to design algorithms and models that efficiently and robustly adapt to unseen tasks.
-
20 Oct 2022 1 repository listed Syntology official (archive's flag): 8 ran · 8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified (of 11 harvested samples) · 2 pointer-only (licence)Longform media such as movies have complex narrative structures, with events spanning a rich variety of ambient visual scenes.
-
6 Sep 2022 1 repository listedCapsule networks are a neural network architecture specialized for visual scene recognition.
-
6 May 2022 1 repository listedFinally, our SSF allows our framework to learn the same scene scheme from multi-grain instance representations and fuses them, so that the entire framework is optimized as a whole.
-
29 Apr 2022 1 repository listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 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 (of 1 harvested sample)
-
23 Dec 2021 1 repository listed
-
25 Sep 2021 1 repository listed
-
1 Aug 2021 1 repository listed
-
1 Aug 2021 1 repository listed
-
8 Jul 2021 1 repository listed
-
22 Apr 2021 1 repository listed
-
7 Apr 2021 1 repository listed
-
26 Mar 2021 1 repository listed
-
26 Mar 2021 1 repository listed
-
10 Mar 2021 1 repository listed
-
1 Jan 2021 1 repository listed
-
18 May 2020 1 repository listed
-
26 Apr 2020 1 repository listed
-
30 Mar 2020 1 repository listed
-
3 Mar 2020 1 repository listed
-
5 Sep 2019 1 repository listed Syntology official (archive's flag): 3 ran · 3 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; 0 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples)
-
28 Aug 2019 1 repository listed
-
1 Aug 2019 1 repository listed
-
10 Jul 2019 1 repository listed
-
28 Apr 2019 1 repository listed
-
29 Mar 2019 1 repository listed
-
2 Jan 2019 1 repository listed
-
11 Aug 2018 1 repository listed
-
23 Jul 2018 1 repository listed
-
14 May 2018 1 repository listed
-
26 Mar 2018 1 repository listed
-
Depth CNNs for RGB-D scene recognition: learning from scratch better than transferring from RGB-CNNs21 Jan 2018 1 repository listed
-
1 Jul 2017 1 repository listed
-
1 Jul 2017 1 repository listed
-
21 Feb 2017 1 repository listed
-
8 Dec 2016 1 repository listed
-
4 Dec 2016 1 repository listed
-
1 Sep 2016 1 repository listed
-
11 Jul 2016 1 repository listed
-
1 Jun 2015 1 repository listed
-
8 May 2015 1 repository listed
-
22 Dec 2014 1 repository listed
-
Open-Vocabulary Semantic Segmentation with Uncertainty Alignment for Robotic Scene Understanding in Indoor Building Environments29 Mar 2025 0 repositories listed
-
Lightweight Multimodal Artificial Intelligence Framework for Maritime Multi-Scene Recognition10 Mar 2025 0 repositories listed
-
Contrastive Visual Data Augmentation24 Feb 2025 0 repositories listed
-
Seeing with Partial Certainty: Conformal Prediction for Robotic Scene Recognition in Built Environments9 Jan 2025 0 repositories listed
-
Vision-Language Models for Autonomous Driving: CLIP-Based Dynamic Scene Understanding9 Jan 2025 0 repositories listed
-
SAIST: Segment Any Infrared Small Target Model Guided by Contrastive Language-Image Pretraining1 Jan 2025 0 repositories listed
-
Movement Control of Smart Mosque's Domes using CSRNet and Fuzzy Logic Techniques13 Oct 2024 0 repositories listed
-
Rethinking VLMs and LLMs for Image Classification3 Oct 2024 0 repositories listed
-
Less yet robust: crucial region selection for scene recognition23 Sep 2024 0 repositories listed
-
CARIn: Constraint-Aware and Responsive Inference on Heterogeneous Devices for Single- and Multi-DNN Workloads2 Sep 2024 0 repositories listed
-
Indoor scene recognition from images under visual corruptions23 Aug 2024 0 repositories listed
-
Vision Language Model for Interpretable and Fine-grained Detection of Safety Compliance in Diverse Workplaces13 Aug 2024 0 repositories listed
-
Multi-task Prompt Words Learning for Social Media Content Generation10 Jul 2024 0 repositories listed
-
Advancing Ubiquitous Wireless Connectivity through Channel Twinning18 Jun 2024 0 repositories listed
-
Non-negative Subspace Feature Representation for Few-shot Learning in Medical Imaging3 Apr 2024 0 repositories listed
-
TextBlockV2: Towards Precise-Detection-Free Scene Text Spotting with Pre-trained Language Model15 Mar 2024 0 repositories listed
-
A Survey of Vision Transformers in Autonomous Driving: Current Trends and Future Directions12 Mar 2024 0 repositories listed
-
Leveraging Self-Supervised Learning for Scene Classification in Child Sexual Abuse Imagery2 Mar 2024 0 repositories listed
-
Digital Divides in Scene Recognition: Uncovering Socioeconomic Biases in Deep Learning Systems23 Jan 2024 0 repositories listed
-
Knowledge-enhanced Multi-perspective Video Representation Learning for Scene Recognition9 Jan 2024 0 repositories listed
-
Inter-object Discriminative Graph Modeling for Indoor Scene Recognition10 Nov 2023 0 repositories listed
-
A Multi-Modal Foundation Model to Assist People with Blindness and Low Vision in Environmental Interaction31 Oct 2023 0 repositories listed
-
Video Scene Location Recognition with Neural Networks21 Sep 2023 0 repositories listed
-
Semantic-embedded Similarity Prototype for Scene Recognition11 Aug 2023 0 repositories listed
-
EnTri: Ensemble Learning with Tri-level Representations for Explainable Scene Recognition23 Jul 2023 0 repositories listed
-
Multi-query Vehicle Re-identification: Viewpoint-conditioned Network, Unified Dataset and New Metric25 May 2023 0 repositories listed
-
Semantic-guided modeling of spatial relation and object co-occurrence for indoor scene recognition22 May 2023 0 repositories listed
-
GeoNet: Benchmarking Unsupervised Adaptation across Geographies27 Mar 2023 0 repositories listed
-
Synergy between human and machine approaches to sound/scene recognition and processing: An overview of ICASSP special session20 Feb 2023 0 repositories listed
-
Attentional Graph Convolutional Network for Structure-aware Audio-Visual Scene Classification31 Dec 2022 0 repositories listed
-
Coarse-to-fine Task-driven Inpainting for Geoscience Images20 Nov 2022 0 repositories listed
-
Ambiguity-Aware Multi-Object Pose Optimization for Visually-Assisted Robot Manipulation2 Nov 2022 0 repositories listed
Syntology lines on 9 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections