{"total":42,"rows":[{"id":"2410.19317","title":"FairMT-Bench: Benchmarking Fairness for Multi-turn Dialogue in Conversational LLMs","created":"2024-10-25","cited_by_count":36,"area":null},{"id":"2407.08126","title":"Label-anticipated Event Disentanglement for Audio-Visual Video Parsing","created":"2024-07-11","cited_by_count":25,"area":null},{"id":"2407.05311","title":"MMAD: Multi-label Micro-Action Detection in Videos","created":"2024-07-07","cited_by_count":20,"area":null},{"id":"2407.04490","title":"Micro-gesture Online Recognition using Learnable Query Points","created":"2024-07-05","cited_by_count":18,"area":null},{"id":"2408.03097","title":"Prototype Learning for Micro-gesture Classification","created":"2024-08-06","cited_by_count":18,"area":null},{"id":"2504.10920","title":"Towards Efficient Partially Relevant Video Retrieval with Active Moment Discovering","created":"2025-04-15","cited_by_count":18,"area":null},{"id":"2507.08344","title":"MM-Gesture: Towards Precise Micro-Gesture Recognition through Multimodal Fusion","created":"2025-07-11","cited_by_count":14,"area":null},{"id":"2412.07233","title":"Repetitive Action Counting with Hybrid Temporal Relation Modeling","created":"2024-12-10","cited_by_count":13,"area":null},{"id":"2507.09512","title":"Online Micro-gesture Recognition Using Data Augmentation and Spatial-Temporal Attention","created":"2025-07-13","cited_by_count":11,"area":null},{"id":"2405.13206","title":"Identity-free Artificial Emotional Intelligence via Micro-Gesture Understanding","created":"2024-05-21","cited_by_count":8,"area":null},{"id":"2605.26441","title":"Rethinking Weakly-supervised Video Temporal Grounding From a Game Perspective","created":"2026-05-26","cited_by_count":8,"area":null},{"id":"2503.15978","title":"A Survey on fMRI-based Brain Decoding for Reconstructing Multimodal Stimuli","created":"2025-03-20","cited_by_count":7,"area":null},{"id":"2511.17490","title":"Video-R4: Reinforcing Text-Rich Video Reasoning with Visual Rumination","created":"2025-11-21","cited_by_count":6,"area":null},{"id":"2409.14319","title":"Scene-Text Grounding for Text-Based Video Question Answering","created":"2024-09-22","cited_by_count":5,"area":null},{"id":"2502.01181","title":"BVINet: Unlocking Blind Video Inpainting with Zero Annotations","created":"2025-02-03","cited_by_count":4,"area":null},{"id":"2508.12411","title":"The Cultural Gene of Large Language Models: A Study on the Impact of Cross-Corpus Training on Model Values and Biases","created":"2025-08-17","cited_by_count":4,"area":null},{"id":"2606.08566","title":"Towards Accurate Emotion-Attributed Video Captioning via Fine-grained Emotion-Cause Pair Extraction","created":"2026-06-07","cited_by_count":4,"area":null},{"id":"2606.09261","title":"Self-supervised Learning Matters: A Simple Ensemble Solution for Micro-Gesture Recognition","created":"2026-06-08","cited_by_count":4,"area":null},{"id":"2504.08581","title":"FMLGS: Fast Multilevel Language Embedded Gaussians for Part-level Interactive Agents","created":"2025-04-11","cited_by_count":3,"area":null},{"id":"2506.12481","title":"Exploring Audio Cues for Enhanced Test-Time Video Model Adaptation","created":"2025-06-14","cited_by_count":3,"area":null},{"id":"2606.31249","title":"Rethinking the Role of Feature Engineering and Learning Strategies in Few-Shot Hidden Emotion Recognition","created":"2026-06-30","cited_by_count":3,"area":null},{"id":"2405.02961","title":"JOSENet: A Joint Stream Embedding Network for Violence Detection in Surveillance Videos","created":"2024-05-05","cited_by_count":2,"area":null},{"id":"2511.00524","title":"Text-guided Fine-Grained Video Anomaly Understanding","created":"2025-11-01","cited_by_count":2,"area":null},{"id":"2410.16642","title":"Fire and Smoke Detection with Burning Intensity Representation","created":"2024-10-22","cited_by_count":1,"area":null},{"id":"2504.07029","title":"Distilling Textual Priors from LLM to Efficient Image Fusion","created":"2025-04-09","cited_by_count":1,"area":null},{"id":"2504.07785","title":"Towards Micro-Action Recognition with Limited Annotations: An Asynchronous Pseudo Labeling and Training Approach","created":"2025-04-10","cited_by_count":1,"area":null},{"id":"2508.07185","title":"DySK-Attn: A Framework for Efficient, Real-Time Knowledge Updating in Large Language Models via Dynamic Sparse Knowledge Attention","created":"2025-08-10","cited_by_count":1,"area":null},{"id":"2509.01455","title":"Trusted Uncertainty in Large Language Models: A Unified Framework for Confidence Calibration and Risk-Controlled Refusal","created":"2025-09-01","cited_by_count":1,"area":null},{"id":"2509.21261","title":"Every Subtlety Counts: Fine-grained Person Independence Micro-Action Recognition via Distributionally Robust Optimization","created":"2025-09-25","cited_by_count":1,"area":null},{"id":"2508.10426","title":"Computational Economics in Large Language Models: Exploring Model Behavior and Incentive Design under Resource Constraints","created":"2025-08-14","cited_by_count":0,"area":null},{"id":"2509.09151","title":"Video Understanding by Design: How Datasets Shape Video Models","created":"2025-09-11","cited_by_count":0,"area":null},{"id":"2510.13390","title":"Generalizing WiFi Gesture Recognition via Large-Model-Aware Semantic Distillation and Alignment","created":"2025-10-15","cited_by_count":0,"area":null},{"id":"2601.00311","title":"ReMA: A Training-Free Plug-and-Play Mixing Augmentation for Video Behavior Recognition","created":"2026-01-01","cited_by_count":0,"area":null},{"id":"2603.07559","title":"Active Inference for Micro-Gesture Recognition: EFE-Guided Temporal Sampling and Adaptive Learning","created":"2026-03-08","cited_by_count":0,"area":null},{"id":"2603.16269","title":"FG-SGL: Fine-Grained Semantic Guidance Learning via Motion Process Decomposition for Micro-Gesture Recognition","created":"2026-03-17","cited_by_count":0,"area":null},{"id":"2604.21011","title":"Micro-DualNet: Dual-Path Spatio-Temporal Network for Micro-Action Recognition","created":"2026-04-22","cited_by_count":0,"area":null},{"id":"2604.22388","title":"HFS-TriNet: A Three-Branch Collaborative Feature Learning Network for Prostate Cancer Classification from TRUS Videos","created":"2026-04-24","cited_by_count":0,"area":null},{"id":"2606.11645","title":"Motion Reinforces Appearance: RGB-Skeleton Gated Residual Fusion for Micro-Gesture Online Recognition","created":"2026-06-10","cited_by_count":0,"area":null},{"id":"2606.13030","title":"A Multi-Modal Framework with Cross-Subject Pseudo-Labeling and Semantic Alignment for Micro-Gesture Recognition","created":"2026-06-11","cited_by_count":0,"area":null},{"id":"2606.14096","title":"A New Multi-Domain Benchmark for Micro-Action Recognition and Detection","created":"2026-06-12","cited_by_count":0,"area":null},{"id":"2607.02670","title":"A Granularity-Aware EEG Feature Framework for Psychopathology Dimension Prediction","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2608.06691","title":"CoDAT: Collaborative Dual-Attention Transformer with Low-Cost Temporal Modeling for Efficient Edge Action Recognition","created":"2026-08-07","cited_by_count":0,"area":null}],"next_cursor":null}