{"total":42,"rows":[{"id":"2203.09463","title":"FERV39k: A Large-Scale Multi-Scene Dataset for Facial Expression Recognition in Videos","created":"2022-03-17","cited_by_count":69,"area":null},{"id":"2201.05991","title":"Video Transformers: A Survey","created":"2022-01-16","cited_by_count":63,"area":null},{"id":"2102.02751","title":"Semi-Supervised Action Recognition with Temporal Contrastive Learning","created":"2021-02-04","cited_by_count":50,"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":"2303.08914","title":"MAtch, eXpand and Improve: Unsupervised Finetuning for Zero-Shot Action Recognition with Language Knowledge","created":"2023-03-15","cited_by_count":43,"area":null},{"id":"2303.02982","title":"CLIP-guided Prototype Modulating for Few-shot Action Recognition","created":"2023-03-06","cited_by_count":41,"area":null},{"id":"2105.05165","title":"AdaMML: Adaptive Multi-Modal Learning for Efficient Video Recognition","created":"2021-05-11","cited_by_count":36,"area":null},{"id":"2108.10394","title":"Dynamic Network Quantization for Efficient Video Inference","created":"2021-08-23","cited_by_count":36,"area":null},{"id":"2110.06513","title":"Benchmarking the Robustness of Spatial-Temporal Models Against Corruptions","created":"2021-10-13","cited_by_count":34,"area":null},{"id":"2203.10233","title":"DirecFormer: A Directed Attention in Transformer Approach to Robust Action Recognition","created":"2022-03-19","cited_by_count":31,"area":null},{"id":"2207.01398","title":"Large-scale Robustness Analysis of Video Action Recognition Models","created":"2022-07-04","cited_by_count":29,"area":null},{"id":"2106.14104","title":"Can An Image Classifier Suffice For Action Recognition?","created":"2021-06-26","cited_by_count":20,"area":null},{"id":"2202.12690","title":"On Modality Bias Recognition and Reduction","created":"2022-02-25","cited_by_count":20,"area":null},{"id":"2302.14309","title":"Temporal Coherent Test-Time Optimization for Robust Video Classification","created":"2023-02-28","cited_by_count":15,"area":null},{"id":"2412.11228","title":"Uni-AdaFocus: Spatial-temporal Dynamic Computation for Video Recognition","created":"2024-12-15","cited_by_count":9,"area":null},{"id":"2110.15639","title":"Multi-Task and Multi-Modal Learning for RGB Dynamic Gesture Recognition","created":"2021-10-29","cited_by_count":7,"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":"2302.04177","title":"A Dynamic Graph CNN with Cross-Representation Distillation for Event-Based Recognition","created":"2023-02-08","cited_by_count":7,"area":null},{"id":"2312.13746","title":"Video Recognition in Portrait Mode","created":"2023-12-21","cited_by_count":6,"area":null},{"id":"2410.03302","title":"Action Selection Learning for Multi-label Multi-view Action Recognition","created":"2024-10-04","cited_by_count":6,"area":null},{"id":"2403.13850","title":"Spatio-Temporal Fluid Dynamics Modeling via Physical-Awareness and Parameter Diffusion Guidance","created":"2024-03-18","cited_by_count":5,"area":null},{"id":"2207.05182","title":"Fine-grained Activities of People Worldwide","created":"2022-07-11","cited_by_count":4,"area":null},{"id":"2406.15034","title":"SVFormer: A Direct Training Spiking Transformer for Efficient Video Action Recognition","created":"2024-06-21","cited_by_count":3,"area":null},{"id":"2111.09976","title":"M2A: Motion Aware Attention for Accurate Video Action Recognition","created":"2021-11-18","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":"2206.11459","title":"Explore Spatio-temporal Aggregation for Insubstantial Object Detection: Benchmark Dataset and Baseline","created":"2022-06-23","cited_by_count":2,"area":null},{"id":"2209.07474","title":"On the Surprising Effectiveness of Transformers in Low-Labeled Video Recognition","created":"2022-09-15","cited_by_count":2,"area":null},{"id":"2308.13870","title":"Brain-like representational straightening of natural movies in robust feedforward neural networks","created":"2023-08-26","cited_by_count":2,"area":null},{"id":"2309.09534","title":"Selective Volume Mixup for Video Action Recognition","created":"2023-09-18","cited_by_count":2,"area":null},{"id":"2204.11929","title":"Temporal Relevance Analysis for Video Action Models","created":"2022-04-25","cited_by_count":1,"area":null},{"id":"2407.16344","title":"SOAP: Enhancing Spatio-Temporal Relation and Motion Information Capturing for Few-Shot Action Recognition","created":"2024-07-23","cited_by_count":1,"area":null},{"id":"2502.12415","title":"Gaseous Object Detection","created":"2025-02-18","cited_by_count":1,"area":null},{"id":"2512.14439","title":"VICTOR: Dataset Copyright Auditing in Video Recognition Systems","created":"2025-12-16","cited_by_count":1,"area":null},{"id":"2203.13281","title":"Movie Genre Classification by Language Augmentation and Shot Sampling","created":"2022-03-24","cited_by_count":0,"area":null},{"id":"2208.10077","title":"Identifying Auxiliary or Adversarial Tasks Using Necessary Condition Analysis for Adversarial Multi-task Video Understanding","created":"2022-08-22","cited_by_count":0,"area":null},{"id":"2211.13694","title":"Hand Guided High Resolution Feature Enhancement for Fine-Grained Atomic Action Segmentation within Complex Human Assemblies","created":"2022-11-24","cited_by_count":0,"area":null},{"id":"2311.14281","title":"Multi-modal Instance Refinement for Cross-domain Action Recognition","created":"2023-11-24","cited_by_count":0,"area":null},{"id":"2403.06616","title":"Density-Guided Label Smoothing for Temporal Localization of Driving Actions","created":"2024-03-11","cited_by_count":0,"area":null},{"id":"2405.03311","title":"Federated Learning for Drowsiness Detection in Connected Vehicles","created":"2024-05-06","cited_by_count":0,"area":null},{"id":"2604.10078","title":"Attention-Guided Dual-Stream Learning for Group Engagement Recognition: Fusing Transformer-Encoded Motion Dynamics with Scene Context via Adaptive Gating","created":"2026-04-11","cited_by_count":0,"area":null},{"id":"2606.25298","title":"KidRisk: Benchmark Dataset for Children Dangerous Action Recognition","created":"2026-06-24","cited_by_count":0,"area":null},{"id":"2606.31421","title":"Temporal Preservation over Processing: Diagnosing and Designing Spatiotemporal Single-Stage Video Detectors","created":"2026-06-30","cited_by_count":0,"area":null}],"next_cursor":null}