{"list":"other","total":57,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1411.5726","title":"CIDEr: Consensus-based Image Description Evaluation","created":"2014-11-20","cited_by_count":2046},{"id":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"id":"1812.03982","title":"SlowFast Networks for Video Recognition","created":"2018-12-10","cited_by_count":1867},{"id":"2102.05095","title":"Is Space-Time Attention All You Need for Video Understanding?","created":"2021-02-09","cited_by_count":1620},{"id":"1801.07455","title":"Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition","created":"2018-01-23","cited_by_count":1209},{"id":"2106.13230","title":"Video Swin Transformer","created":"2021-06-24","cited_by_count":1091},{"id":"1406.2199","title":"Two-Stream Convolutional Networks for Action Recognition in Videos","created":"2014-06-09","cited_by_count":1068},{"id":"1811.08383","title":"TSM: Temporal Shift Module for Efficient Video Understanding","created":"2018-11-20","cited_by_count":856},{"id":"2112.01526","title":"MViTv2: Improved Multiscale Vision Transformers for Classification and Detection","created":"2021-12-02","cited_by_count":519},{"id":"1411.4389","title":"Long-term Recurrent Convolutional Networks for Visual Recognition and Description","created":"2014-11-17","cited_by_count":484},{"id":"1711.08496","title":"Temporal Relational Reasoning in Videos","created":"2017-11-22","cited_by_count":324},{"id":"1705.02953","title":"Temporal Segment Networks for Action Recognition in Videos","created":"2017-05-08","cited_by_count":279},{"id":"2401.13601","title":"MM-LLMs: Recent Advances in MultiModal Large Language Models","created":"2024-01-24","cited_by_count":278},{"id":"1806.02964","title":"BSN: Boundary Sensitive Network for Temporal Action Proposal Generation","created":"2018-06-08","cited_by_count":271},{"id":"1704.06228","title":"Temporal Action Detection with Structured Segment Networks","created":"2017-04-20","cited_by_count":267},{"id":"2302.14115","title":"Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning","created":"2023-02-27","cited_by_count":263},{"id":"1702.01992","title":"Gated Multimodal Units for Information Fusion","created":"2017-02-07","cited_by_count":248},{"id":"2004.06704","title":"FineGym: A Hierarchical Video Dataset for Fine-grained Action Understanding","created":"2020-04-14","cited_by_count":234},{"id":"1604.06182","title":"The THUMOS Challenge on Action Recognition for Videos \"in the Wild\"","created":"2016-04-21","cited_by_count":213},{"id":"2312.17432","title":"Video Understanding with Large Language Models: A Survey","created":"2023-12-29","cited_by_count":206},{"id":"2111.13196","title":"SwinBERT: End-to-End Transformers with Sparse Attention for Video Captioning","created":"2021-11-25","cited_by_count":162},{"id":"2108.07781","title":"End-to-End Dense Video Captioning with Parallel Decoding","created":"2021-08-17","cited_by_count":133},{"id":"2204.03646","title":"FineDiving: A Fine-grained Dataset for Procedure-aware Action Quality Assessment","created":"2022-04-07","cited_by_count":107},{"id":"1904.04346","title":"What and How Well You Performed? A Multitask Learning Approach to Action Quality Assessment","created":"2019-04-08","cited_by_count":100},{"id":"1611.05125","title":"Learning To Score Olympic Events","created":"2016-11-16","cited_by_count":88},{"id":"1812.06367","title":"Action Quality Assessment Across Multiple Actions","created":"2018-12-15","cited_by_count":79},{"id":"2411.17558","title":"Natural Language Understanding and Inference with MLLM in Visual Question Answering: A Survey","created":"2024-11-26","cited_by_count":76},{"id":"1811.10696","title":"Attentive Relational Networks for Mapping Images to Scene Graphs","created":"2018-11-26","cited_by_count":73},{"id":"2206.07160","title":"LAVENDER: Unifying Video-Language Understanding as Masked Language Modeling","created":"2022-06-14","cited_by_count":73},{"id":"1902.10322","title":"Spatio-Temporal Dynamics and Semantic Attribute Enriched Visual Encoding for Video Captioning","created":"2019-02-27","cited_by_count":60},{"id":"1506.03607","title":"P-CNN: Pose-based CNN Features for Action Recognition","created":"2015-06-11","cited_by_count":58},{"id":"2203.15187","title":"ASM-Loc: Action-aware Segment Modeling for Weakly-Supervised Temporal Action Localization","created":"2022-03-29","cited_by_count":40},{"id":"2411.18894","title":"T2SG: Traffic Topology Scene Graph for Topology Reasoning in Autonomous Driving","created":"2024-11-28","cited_by_count":35},{"id":"2203.02925","title":"Weakly Supervised Temporal Action Localization via Representative Snippet Knowledge Propagation","created":"2022-03-06","cited_by_count":32},{"id":"2303.11048","title":"SGFormer: Semantic Graph Transformer for Point Cloud-based 3D Scene Graph Generation","created":"2023-03-20","cited_by_count":27},{"id":"2501.03674","title":"Action Quality Assessment via Hierarchical Pose-guided Multi-stage Contrastive Regression","created":"2025-01-07","cited_by_count":21},{"id":"2502.12425","title":"Robust Disentangled Counterfactual Learning for Physical Audiovisual Commonsense Reasoning","created":"2025-02-18","cited_by_count":20},{"id":"2508.10922","title":"A Survey on Video Temporal Grounding with Multimodal Large Language Model","created":"2025-08-07","cited_by_count":20},{"id":"2303.09706","title":"Unsupervised Self-Driving Attention Prediction via Uncertainty Mining and Knowledge Embedding","created":"2023-03-17","cited_by_count":19},{"id":"2404.14471","title":"Narrative Action Evaluation with Prompt-Guided Multimodal Interaction","created":"2024-04-22","cited_by_count":19},{"id":"2407.08101","title":"What to Say and When to Say it: Live Fitness Coaching as a Testbed for Situated Interaction","created":"2024-07-11","cited_by_count":18},{"id":"2407.08583","title":"The Synergy between Data and Multi-Modal Large Language Models: A Survey from Co-Development Perspective","created":"2024-07-11","cited_by_count":15},{"id":"2507.21585","title":"SafeDriveRAG: Towards Safe Autonomous Driving with Knowledge Graph-based Retrieval-Augmented Generation","created":"2025-07-29","cited_by_count":15},{"id":"2310.19559","title":"Disentangled Counterfactual Learning for Physical Audiovisual Commonsense Reasoning","created":"2023-10-30","cited_by_count":13},{"id":"2408.02138","title":"RICA2: Rubric-Informed, Calibrated Assessment of Actions","created":"2024-08-04","cited_by_count":13},{"id":"2411.08466","title":"Weakly Supervised Temporal Action Localization via Dual-Prior Collaborative Learning Guided by Multimodal Large Language Models","created":"2024-11-13","cited_by_count":10},{"id":"2401.02841","title":"Multi-Stage Contrastive Regression for Action Quality Assessment","created":"2024-01-05","cited_by_count":8},{"id":"2407.19675","title":"Semi-Supervised Teacher-Reference-Student Architecture for Action Quality Assessment","created":"2024-07-29","cited_by_count":8},{"id":"2408.08488","title":"PITN: Physics-Informed Temporal Networks for Cuffless Blood Pressure Estimation","created":"2024-08-16","cited_by_count":8},{"id":"2507.20163","title":"Player-Centric Multimodal Prompt Generation for Large Language Model Based Identity-Aware Basketball Video Captioning","created":"2025-07-27","cited_by_count":7},{"id":"2102.07355","title":"Win-Fail Action Recognition","created":"2021-02-15","cited_by_count":4},{"id":"2507.16287","title":"Beyond Label Semantics: Language-Guided Action Anatomy for Few-shot Action Recognition","created":"2025-07-22","cited_by_count":2},{"id":"2508.16291","title":"Learning Long-Range Action Representation by Two-Stream Mamba Pyramid Network for Figure Skating Assessment","created":"2025-08-22","cited_by_count":2}],"next_cursor":null}