{"list":"other","total":56,"rows":[{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"2412.05271","title":"Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling","created":"2024-12-06","cited_by_count":1599},{"id":"1706.04261","title":"The \"something something\" video database for learning and evaluating visual common sense","created":"2017-06-13","cited_by_count":1103},{"id":"2310.13548","title":"Towards Understanding Sycophancy in Language Models","created":"2023-10-20","cited_by_count":1040},{"id":"1906.03327","title":"HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips","created":"2019-06-07","cited_by_count":950},{"id":"1804.02748","title":"Scaling Egocentric Vision: The EPIC-KITCHENS Dataset","created":"2018-04-08","cited_by_count":795},{"id":"2109.14084","title":"VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding","created":"2021-09-28","cited_by_count":602},{"id":"2410.02713","title":"LLaVA-Video: Video Instruction Tuning With Synthetic Data","created":"2024-10-03","cited_by_count":583},{"id":"1604.01753","title":"Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding","created":"2016-04-06","cited_by_count":537},{"id":"1905.04757","title":"NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding","created":"2019-05-12","cited_by_count":533},{"id":"2501.13106","title":"VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding","created":"2025-01-22","cited_by_count":518},{"id":"1910.01442","title":"CLEVRER: CoLlision Events for Video REpresentation and Reasoning","created":"2019-10-03","cited_by_count":484},{"id":"1705.08421","title":"AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions","created":"2017-05-23","cited_by_count":449},{"id":"2208.02816","title":"Expanding Language-Image Pretrained Models for General Video Recognition","created":"2022-08-04","cited_by_count":321},{"id":"1912.06992","title":"Action Genome: Actions as Composition of Spatio-temporal Scene Graphs","created":"2019-12-15","cited_by_count":250},{"id":"2004.06704","title":"FineGym: A Hierarchical Video Dataset for Fine-grained Action Understanding","created":"2020-04-14","cited_by_count":234},{"id":"1801.03150","title":"Moments in Time Dataset: one million videos for event understanding","created":"2018-01-09","cited_by_count":215},{"id":"2212.03640","title":"Fine-tuned CLIP Models are Efficient Video Learners","created":"2022-12-06","cited_by_count":179},{"id":"2405.20797","title":"Ovis: Structural Embedding Alignment for Multimodal Large Language Model","created":"2024-05-31","cited_by_count":169},{"id":"2409.12961","title":"Oryx MLLM: On-Demand Spatial-Temporal Understanding at Arbitrary Resolution","created":"2024-09-19","cited_by_count":159},{"id":"1804.04527","title":"SoccerNet: A Scalable Dataset for Action Spotting in Soccer Videos","created":"2018-04-12","cited_by_count":150},{"id":"2203.15086","title":"X-Pool: Cross-Modal Language-Video Attention for Text-Video Retrieval","created":"2022-03-28","cited_by_count":128},{"id":"1912.05534","title":"Why Can't I Dance in the Mall? Learning to Mitigate Scene Bias in Action Recognition","created":"2019-12-11","cited_by_count":117},{"id":"2502.08177","title":"SycEval: Evaluating LLM Sycophancy","created":"2025-02-12","cited_by_count":108},{"id":"2508.11737","title":"Ovis2.5 Technical Report","created":"2025-08-15","cited_by_count":108},{"id":"2411.15287","title":"Sycophancy in Large Language Models: Causes and Mitigations","created":"2024-11-22","cited_by_count":101},{"id":"1507.05738","title":"Every Moment Counts: Dense Detailed Labeling of Actions in Complex Videos","created":"2015-07-21","cited_by_count":93},{"id":"2110.06615","title":"CLIP4Caption: CLIP for Video Caption","created":"2021-10-13","cited_by_count":88},{"id":"2205.00823","title":"CenterCLIP: Token Clustering for Efficient Text-Video Retrieval","created":"2022-05-02","cited_by_count":86},{"id":"1911.11206","title":"Oops! Predicting Unintentional Action in Video","created":"2019-11-25","cited_by_count":82},{"id":"2005.00214","title":"The AVA-Kinetics Localized Human Actions Video Dataset","created":"2020-05-01","cited_by_count":82},{"id":"2007.00631","title":"Causal Discovery in Physical Systems from Videos","created":"2020-07-01","cited_by_count":77},{"id":"1904.12634","title":"DADA-2000: Can Driving Accident be Predicted by Driver Attention? Analyzed by A Benchmark","created":"2019-04-23","cited_by_count":57},{"id":"2302.00624","title":"Open-VCLIP: Transforming CLIP to an Open-vocabulary Video Model via Interpolated Weight Optimization","created":"2023-02-01","cited_by_count":55},{"id":"2507.20939","title":"ARC-Hunyuan-Video-7B: Structured Video Comprehension of Real-World Shorts","created":"2025-07-28","cited_by_count":41},{"id":"2402.03241","title":"FROSTER: Frozen CLIP Is A Strong Teacher for Open-Vocabulary Action Recognition","created":"2024-02-05","cited_by_count":36},{"id":"1912.07249","title":"Mimetics: Towards Understanding Human Actions Out of Context","created":"2019-12-16","cited_by_count":32},{"id":"2403.02738","title":"Causal Prompting: Debiasing Large Language Model Prompting based on Front-Door Adjustment","created":"2024-03-05","cited_by_count":30},{"id":"2106.13364","title":"CausalCity: Complex Simulations with Agency for Causal Discovery and Reasoning","created":"2021-06-25","cited_by_count":23},{"id":"2409.17647","title":"MECD: Unlocking Multi-Event Causal Discovery in Video Reasoning","created":"2024-09-26","cited_by_count":23},{"id":"2501.05901","title":"Valley2: Exploring Multimodal Models with Scalable Vision-Language Design","created":"2025-01-10","cited_by_count":21},{"id":"2411.18042","title":"HyperGLM: HyperGraph for Video Scene Graph Generation and Anticipation","created":"2024-11-27","cited_by_count":19},{"id":"2209.01425","title":"Dynamic Spatio-Temporal Specialization Learning for Fine-Grained Action Recognition","created":"2022-09-03","cited_by_count":17},{"id":"2510.11822","title":"Beyond Consensus: Mitigating the Agreeableness Bias in LLM Judge Evaluations","created":"2025-10-13","cited_by_count":16},{"id":"2406.16605","title":"CLEAR: Can Language Models Really Understand Causal Graphs?","created":"2024-06-24","cited_by_count":14},{"id":"2309.01265","title":"SOAR: Scene-debiasing Open-set Action Recognition","created":"2023-09-03","cited_by_count":12},{"id":"2407.07612","title":"Teaching Transformers Causal Reasoning through Axiomatic Training","created":"2024-07-10","cited_by_count":12},{"id":"2209.09393","title":"Mitigating Representation Bias in Action Recognition: Algorithms and Benchmarks","created":"2022-09-20","cited_by_count":7},{"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},{"id":"2506.08553","title":"From Pixels to Graphs: using Scene and Knowledge Graphs for HD-EPIC VQA Challenge","created":"2025-06-10","cited_by_count":6},{"id":"2502.00156","title":"ALBAR: Adversarial Learning approach to mitigate Biases in Action Recognition","created":"2025-01-31","cited_by_count":5},{"id":"2508.00399","title":"iSafetyBench: A video-language benchmark for safety in industrial environment","created":"2025-08-01","cited_by_count":5},{"id":"2509.11862","title":"Bridging Vision Language Models and Symbolic Grounding for Video Question Answering","created":"2025-09-15","cited_by_count":4},{"id":"2506.06910","title":"Causal Graph based Event Reasoning using Semantic Relation Experts","created":"2025-06-07","cited_by_count":2},{"id":"2508.00085","title":"Punching Bag vs. Punching Person: Motion Transferability in Videos","created":"2025-07-31","cited_by_count":1}],"next_cursor":null}