{"total":117,"rows":[{"id":"2104.01633","title":"MIST: Multiple Instance Self-Training Framework for Video Anomaly Detection","created":"2021-04-04","cited_by_count":138,"area":null},{"id":"2101.07974","title":"TCLR: Temporal Contrastive Learning for Video Representation","created":"2021-01-20","cited_by_count":136,"area":null},{"id":"2107.10161","title":"Evidential Deep Learning for Open Set Action Recognition","created":"2021-07-21","cited_by_count":96,"area":null},{"id":"2210.10352","title":"Temporal Action Segmentation: An Analysis of Modern Techniques","created":"2022-10-19","cited_by_count":85,"area":null},{"id":"2104.09496","title":"Temporal Query Networks for Fine-grained Video Understanding","created":"2021-04-19","cited_by_count":68,"area":null},{"id":"2311.17404","title":"VITATECS: A Diagnostic Dataset for Temporal Concept Understanding of Video-Language Models","created":"2023-11-29","cited_by_count":55,"area":null},{"id":"2404.12391","title":"On the Content Bias in Fr\\'echet Video Distance","created":"2024-04-18","cited_by_count":52,"area":null},{"id":"2110.15128","title":"Contrast and Mix: Temporal Contrastive Video Domain Adaptation with Background Mixing","created":"2021-10-28","cited_by_count":49,"area":null},{"id":"2207.10077","title":"Discover and Mitigate Unknown Biases with Debiasing Alternate Networks","created":"2022-07-20","cited_by_count":47,"area":null},{"id":"2103.10095","title":"On Semantic Similarity in Video Retrieval","created":"2021-03-18","cited_by_count":46,"area":null},{"id":"2104.14556","title":"Discover the Unknown Biased Attribute of an Image Classifier","created":"2021-04-29","cited_by_count":46,"area":null},{"id":"2109.15130","title":"Motion-aware Contrastive Video Representation Learning via Foreground-background Merging","created":"2021-09-30","cited_by_count":45,"area":null},{"id":"2112.03624","title":"Time-Equivariant Contrastive Video Representation Learning","created":"2021-12-07","cited_by_count":44,"area":null},{"id":"2108.03764","title":"PASS: Protected Attribute Suppression System for Mitigating Bias in Face Recognition","created":"2021-08-09","cited_by_count":38,"area":null},{"id":"2210.09520","title":"Using Language to Extend to Unseen Domains","created":"2022-10-18","cited_by_count":34,"area":null},{"id":"2108.05449","title":"Learning Bias-Invariant Representation by Cross-Sample Mutual Information Minimization","created":"2021-08-11","cited_by_count":32,"area":null},{"id":"2202.08926","title":"On Guiding Visual Attention with Language Specification","created":"2022-02-17","cited_by_count":30,"area":null},{"id":"2406.06087","title":"GAIA: Rethinking Action Quality Assessment for AI-Generated Videos","created":"2024-06-10","cited_by_count":30,"area":null},{"id":"2109.01305","title":"Video Pose Distillation for Few-Shot, Fine-Grained Sports Action Recognition","created":"2021-09-03","cited_by_count":29,"area":null},{"id":"2201.09381","title":"vCLIMB: A Novel Video Class Incremental Learning Benchmark","created":"2022-01-23","cited_by_count":28,"area":null},{"id":"2206.04790","title":"Learn2Augment: Learning to Composite Videos for Data Augmentation in Action Recognition","created":"2022-06-09","cited_by_count":27,"area":null},{"id":"2211.12883","title":"Mitigating and Evaluating Static Bias of Action Representations in the Background and the Foreground","created":"2022-11-23","cited_by_count":27,"area":null},{"id":"2206.02846","title":"A Deeper Dive Into What Deep Spatiotemporal Networks Encode: Quantifying Static vs. Dynamic Information","created":"2022-06-06","cited_by_count":26,"area":null},{"id":"2303.12698","title":"Open Set Action Recognition via Multi-Label Evidential Learning","created":"2023-02-27","cited_by_count":26,"area":null},{"id":"2308.11488","title":"Opening the Vocabulary of Egocentric Actions","created":"2023-08-22","cited_by_count":23,"area":null},{"id":"2401.10831","title":"Understanding Video Transformers via Universal Concept Discovery","created":"2024-01-19","cited_by_count":23,"area":"mechinterp"},{"id":"2103.16565","title":"Learning Representational Invariances for Data-Efficient Action Recognition","created":"2021-03-30","cited_by_count":22,"area":null},{"id":"2503.15871","title":"MASH-VLM: Mitigating Action-Scene Hallucination in Video-LLMs through Disentangled Spatial-Temporal Representations","created":"2025-03-20","cited_by_count":22,"area":null},{"id":"2602.07050","title":"Interpreting Physics in Video World Models","created":"2026-02-04","cited_by_count":22,"area":"wm"},{"id":"2504.19475","title":"Prisma: An Open Source Toolkit for Mechanistic Interpretability in Vision and Video","created":"2025-04-28","cited_by_count":21,"area":"mechinterp"},{"id":"2112.05892","title":"COMPOSER: Compositional Reasoning of Group Activity in Videos with Keypoint-Only Modality","created":"2021-12-11","cited_by_count":19,"area":null},{"id":"2303.15270","title":"Unified Keypoint-based Action Recognition Framework via Structured Keypoint Pooling","created":"2023-03-27","cited_by_count":19,"area":null},{"id":"2310.17942","title":"Diversifying Spatial-Temporal Perception for Video Domain Generalization","created":"2023-10-27","cited_by_count":19,"area":null},{"id":"2206.11493","title":"Learning to Refactor Action and Co-occurrence Features for Temporal Action Localization","created":"2022-06-23","cited_by_count":18,"area":null},{"id":"2303.15443","title":"GeoNet: Benchmarking Unsupervised Adaptation across Geographies","created":"2023-03-27","cited_by_count":17,"area":null},{"id":"2207.06261","title":"Is Appearance Free Action Recognition Possible?","created":"2022-07-13","cited_by_count":16,"area":null},{"id":"2207.05340","title":"Dual Contrastive Learning for Spatio-temporal Representation","created":"2022-07-12","cited_by_count":15,"area":null},{"id":"2403.01560","title":"XOV-Action: Towards Generalizable Open-Vocabulary Action Recognition","created":"2024-03-03","cited_by_count":15,"area":null},{"id":"2504.04804","title":"DebGCD: Debiased Learning with Distribution Guidance for Generalized Category Discovery","created":"2025-04-07","cited_by_count":15,"area":null},{"id":"2104.09052","title":"Metadata Normalization","created":"2021-04-19","cited_by_count":14,"area":null},{"id":"2312.08010","title":"EZ-CLIP: Efficient Zeroshot Video Action Recognition","created":"2023-12-13","cited_by_count":14,"area":null},{"id":"2309.03989","title":"CDFSL-V: Cross-Domain Few-Shot Learning for Videos","created":"2023-09-07","cited_by_count":13,"area":null},{"id":"2408.02464","title":"Fairness and Bias Mitigation in Computer Vision: A Survey","created":"2024-08-05","cited_by_count":13,"area":null},{"id":"2103.10574","title":"Hopper: Multi-hop Transformer for Spatiotemporal Reasoning","created":"2021-03-19","cited_by_count":12,"area":null},{"id":"2204.07892","title":"Video Action Detection: Analysing Limitations and Challenges","created":"2022-04-17","cited_by_count":12,"area":null},{"id":"2303.17285","title":"Decomposed Cross-modal Distillation for RGB-based Temporal Action Detection","created":"2023-03-30","cited_by_count":12,"area":null},{"id":"2309.01265","title":"SOAR: Scene-debiasing Open-set Action Recognition","created":"2023-09-03","cited_by_count":12,"area":null},{"id":"2311.18825","title":"CAST: Cross-Attention in Space and Time for Video Action Recognition","created":"2023-11-30","cited_by_count":12,"area":null},{"id":"2307.03353","title":"A Survey of Deep Learning in Sports Applications: Perception, Comprehension, and Decision","created":"2023-07-07","cited_by_count":11,"area":null},{"id":"2203.10694","title":"FAR: Fourier Aerial Video Recognition","created":"2022-03-21","cited_by_count":10,"area":null},{"id":"2203.16632","title":"Controllable Augmentations for Video Representation Learning","created":"2022-03-30","cited_by_count":10,"area":null},{"id":"2206.15015","title":"Exploring Temporally Dynamic Data Augmentation for Video Recognition","created":"2022-06-30","cited_by_count":9,"area":null},{"id":"2203.10719","title":"LocATe: End-to-end Localization of Actions in 3D with Transformers","created":"2022-03-21","cited_by_count":8,"area":null},{"id":"2204.04730","title":"Deep Non-rigid Structure-from-Motion: A Sequence-to-Sequence Translation Perspective","created":"2022-04-10","cited_by_count":8,"area":null},{"id":"2211.00448","title":"Signing Outside the Studio: Benchmarking Background Robustness for Continuous Sign Language Recognition","created":"2022-11-01","cited_by_count":8,"area":null},{"id":"2403.12710","title":"Selective, Interpretable, and Motion Consistent Privacy Attribute Obfuscation for Action Recognition","created":"2024-03-19","cited_by_count":8,"area":null},{"id":"2404.11903","title":"Simultaneous Detection and Interaction Reasoning for Object-Centric Action Recognition","created":"2024-04-18","cited_by_count":8,"area":null},{"id":"2407.10860","title":"Human-Centric Transformer for Domain Adaptive Action Recognition","created":"2024-07-15","cited_by_count":8,"area":null},{"id":"2112.12175","title":"Recur, Attend or Convolve? On Whether Temporal Modeling Matters for Cross-Domain Robustness in Action Recognition","created":"2021-12-22","cited_by_count":7,"area":null},{"id":"2209.09393","title":"Mitigating Representation Bias in Action Recognition: Algorithms and Benchmarks","created":"2022-09-20","cited_by_count":7,"area":null},{"id":"2211.01783","title":"Quantifying and Learning Static vs. Dynamic Information in Deep Spatiotemporal Networks","created":"2022-11-03","cited_by_count":7,"area":null},{"id":"2312.00826","title":"DEVIAS: Learning Disentangled Video Representations of Action and Scene","created":"2023-11-30","cited_by_count":7,"area":null},{"id":"2502.20158","title":"Learning to Generalize without Bias for Open-Vocabulary Action Recognition","created":"2025-02-27","cited_by_count":7,"area":null},{"id":"2201.03668","title":"Towards Group Robustness in the presence of Partial Group Labels","created":"2022-01-10","cited_by_count":6,"area":null},{"id":"2205.06253","title":"What's in a Caption? Dataset-Specific Linguistic Diversity and Its Effect on Visual Description Models and Metrics","created":"2022-05-12","cited_by_count":6,"area":null},{"id":"2207.01708","title":"Disentangled Action Recognition with Knowledge Bases","created":"2022-07-04","cited_by_count":6,"area":null},{"id":"2209.07518","title":"Distribution Aware Metrics for Conditional Natural Language Generation","created":"2022-09-15","cited_by_count":6,"area":null},{"id":"2308.11244","title":"Are current long-term video understanding datasets long-term?","created":"2023-08-22","cited_by_count":6,"area":null},{"id":"2501.12681","title":"Can masking background and object reduce static bias for zero-shot action recognition?","created":"2025-01-22","cited_by_count":6,"area":null},{"id":"2311.06231","title":"Learning Human Action Recognition Representations Without Real Humans","created":"2023-11-10","cited_by_count":5,"area":null},{"id":"2502.00156","title":"ALBAR: Adversarial Learning approach to mitigate Biases in Action Recognition","created":"2025-01-31","cited_by_count":5,"area":null},{"id":"2502.21201","title":"The PanAf-FGBG Dataset: Understanding the Impact of Backgrounds in Wildlife Behaviour Recognition","created":"2025-02-28","cited_by_count":5,"area":null},{"id":"2112.03803","title":"Suppressing Static Visual Cues via Normalizing Flows for Self-Supervised Video Representation Learning","created":"2021-12-07","cited_by_count":4,"area":null},{"id":"2212.13495","title":"Truncate-Split-Contrast: A Framework for Learning from Mislabeled Videos","created":"2022-12-27","cited_by_count":4,"area":null},{"id":"2405.06574","title":"Deep video representation learning: a survey","created":"2024-05-10","cited_by_count":4,"area":null},{"id":"2106.03162","title":"Transformed ROIs for Capturing Visual Transformations in Videos","created":"2021-06-06","cited_by_count":3,"area":null},{"id":"2109.00222","title":"Spatio-Temporal Perturbations for Video Attribution","created":"2021-09-01","cited_by_count":3,"area":null},{"id":"2109.02580","title":"Ultra-high Resolution Image Segmentation via Locality-aware Context Fusion and Alternating Local Enhancement","created":"2021-09-06","cited_by_count":3,"area":null},{"id":"2303.07615","title":"Variation of Gender Biases in Visual Recognition Models Before and After Finetuning","created":"2023-03-14","cited_by_count":3,"area":null},{"id":"2309.02290","title":"ATM: Action Temporality Modeling for Video Question Answering","created":"2023-09-05","cited_by_count":3,"area":"lr"},{"id":"2312.06306","title":"Attribute Annotation and Bias Evaluation in Visual Datasets for Autonomous Driving","created":"2023-12-11","cited_by_count":3,"area":null},{"id":"2409.01448","title":"FinePseudo: Improving Pseudo-Labelling through Temporal-Alignablity for Semi-Supervised Fine-Grained Action Recognition","created":"2024-09-02","cited_by_count":3,"area":null},{"id":"2504.06153","title":"A Large-Scale Analysis on Contextual Self-Supervised Video Representation Learning","created":"2025-04-08","cited_by_count":3,"area":null},{"id":"2111.01215","title":"Gradient Frequency Modulation for Visually Explaining Video Understanding Models","created":"2021-11-01","cited_by_count":2,"area":null},{"id":"2112.00804","title":"PreViTS: Contrastive Pretraining with Video Tracking Supervision","created":"2021-12-01","cited_by_count":2,"area":null},{"id":"2202.00712","title":"Should I take a walk? Estimating Energy Expenditure from Video Data","created":"2022-02-01","cited_by_count":2,"area":null},{"id":"2312.01006","title":"Dual-Teacher De-biasing Distillation Framework for Multi-domain Fake News Detection","created":"2023-12-02","cited_by_count":2,"area":"distill"},{"id":"2409.06665","title":"Data Collection-free Masked Video Modeling","created":"2024-09-10","cited_by_count":2,"area":null},{"id":"2506.09411","title":"Synthetic Human Action Video Data Generation with Pose Transfer","created":"2025-06-11","cited_by_count":2,"area":null},{"id":"2512.01048","title":"TRoVe: Discovering Error-Inducing Static Feature Biases in Temporal Vision-Language Models","created":"2025-11-30","cited_by_count":2,"area":"mllm"},{"id":"2512.17953","title":"Seeing Beyond the Scene: Analyzing and Mitigating Background Bias in Action Recognition","created":"2025-12-17","cited_by_count":2,"area":null},{"id":"2110.07118","title":"Nuisance-Label Supervision: Robustness Improvement by Free Labels","created":"2021-10-14","cited_by_count":1,"area":null},{"id":"2305.08191","title":"Is end-to-end learning enough for fitness activity recognition?","created":"2023-05-14","cited_by_count":1,"area":null},{"id":"2307.04105","title":"Towards Assumption-free Bias Mitigation","created":"2023-07-09","cited_by_count":1,"area":null},{"id":"2311.12467","title":"GLAD: Global-Local View Alignment and Background Debiasing for Unsupervised Video Domain Adaptation with Large Domain Gap","created":"2023-11-21","cited_by_count":1,"area":null},{"id":"2311.12684","title":"Adversarial Reweighting Guided by Wasserstein Distance for Bias Mitigation","created":"2023-11-21","cited_by_count":1,"area":null},{"id":"2508.10896","title":"ESSENTIAL: Episodic and Semantic Memory Integration for Video Class-Incremental Learning","created":"2025-08-14","cited_by_count":1,"area":null},{"id":"2509.02807","title":"PixFoundation 2.0: Do Video Multi-Modal LLMs Use Motion in Visual Grounding?","created":"2025-09-02","cited_by_count":1,"area":"mllm"},{"id":"2511.08666","title":"Privacy Beyond Pixels: Latent Anonymization for Privacy-Preserving Video Understanding","created":"2025-11-11","cited_by_count":1,"area":null},{"id":"2603.25733","title":"SlotVTG: Object-Centric Adapter for Generalizable Video Temporal Grounding","created":"2026-03-26","cited_by_count":1,"area":"mllm"}],"next_cursor":"100"}