{"list":"other","total":62,"rows":[{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"id":"2507.06261","title":"Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities","created":"2025-07-07","cited_by_count":3796},{"id":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"2508.18265","title":"InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency","created":"2025-08-25","cited_by_count":1510},{"id":"2306.02858","title":"Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding","created":"2023-06-05","cited_by_count":1471},{"id":"2405.21075","title":"Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis","created":"2024-05-31","cited_by_count":1413},{"id":"2311.10122","title":"Video-LLaVA: Learning United Visual Representation by Alignment Before Projection","created":"2023-11-16","cited_by_count":1402},{"id":"2104.00650","title":"Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval","created":"2021-04-01","cited_by_count":1177},{"id":"2311.17005","title":"MVBench: A Comprehensive Multi-modal Video Understanding Benchmark","created":"2023-11-28","cited_by_count":1109},{"id":"2306.05424","title":"Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models","created":"2023-06-08","cited_by_count":1062},{"id":"1904.08405","title":"Event-based Vision: A Survey","created":"2019-04-17","cited_by_count":1016},{"id":"2305.06355","title":"VideoChat: Chat-Centric Video Understanding","created":"2023-05-10","cited_by_count":857},{"id":"2111.08897","title":"ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Data","created":"2021-11-17","cited_by_count":454},{"id":"2406.08035","title":"LVBench: An Extreme Long Video Understanding Benchmark","created":"2024-06-12","cited_by_count":410},{"id":"2504.13181","title":"Perception Encoder: The best visual embeddings are not at the output of the network","created":"2025-04-17","cited_by_count":326},{"id":"1507.07629","title":"Converting Static Image Datasets to Spiking Neuromorphic Datasets Using Saccades","created":"2015-07-28","cited_by_count":314},{"id":"1907.06987","title":"A Short Note on the Kinetics-700 Human Action Dataset","created":"2019-07-15","cited_by_count":310},{"id":"2103.06011","title":"DSEC: A Stereo Event Camera Dataset for Driving Scenarios","created":"2021-03-10","cited_by_count":303},{"id":"2406.04264","title":"MLVU: Benchmarking Multi-task Long Video Understanding","created":"2024-06-06","cited_by_count":292},{"id":"1801.10202","title":"The Multi Vehicle Stereo Event Camera Dataset: An Event Camera Dataset for 3D Perception","created":"2018-01-30","cited_by_count":254},{"id":"1904.08298","title":"Events-to-Video: Bringing Modern Computer Vision to Event Cameras","created":"2019-04-17","cited_by_count":193},{"id":"2009.13436","title":"Learning to Detect Objects with a 1 Megapixel Event Camera","created":"2020-09-28","cited_by_count":186},{"id":"1912.03095","title":"Video to Events: Recycling Video Datasets for Event Cameras","created":"2019-12-06","cited_by_count":165},{"id":"1804.09626","title":"Charades-Ego: A Large-Scale Dataset of Paired Third and First Person Videos","created":"2018-04-25","cited_by_count":128},{"id":"2001.08499","title":"A Large Scale Event-based Detection Dataset for Automotive","created":"2020-01-23","cited_by_count":109},{"id":"2112.01041","title":"N-ImageNet: Towards Robust, Fine-Grained Object Recognition with Event Cameras","created":"2021-12-02","cited_by_count":92},{"id":"2504.13180","title":"PerceptionLM: Open-Access Data and Models for Detailed Visual Understanding","created":"2025-04-17","cited_by_count":92},{"id":"2302.08890","title":"Deep Learning for Event-based Vision: A Comprehensive Survey and Benchmarks","created":"2023-02-17","cited_by_count":90},{"id":"2109.09052","title":"Object Tracking by Jointly Exploiting Frame and Event Domain","created":"2021-09-19","cited_by_count":84},{"id":"2501.02955","title":"MotionBench: Benchmarking and Improving Fine-grained Video Motion Understanding for Vision Language Models","created":"2025-01-06","cited_by_count":70},{"id":"2005.08605","title":"DDD20 End-to-End Event Camera Driving Dataset: Fusing Frames and Events with Deep Learning for Improved Steering Prediction","created":"2020-05-18","cited_by_count":56},{"id":"2506.07900","title":"MiniCPM4: Ultra-Efficient LLMs on End Devices","created":"2025-06-09","cited_by_count":52},{"id":"2301.01928","title":"Event Camera Data Pre-training","created":"2023-01-05","cited_by_count":50},{"id":"2211.09648","title":"HARDVS: Revisiting Human Activity Recognition with Dynamic Vision Sensors","created":"2022-11-17","cited_by_count":47},{"id":"2212.10368","title":"Masked Event Modeling: Self-Supervised Pretraining for Event Cameras","created":"2022-12-20","cited_by_count":41},{"id":"2306.06354","title":"EventCLIP: Adapting CLIP for Event-based Object Recognition","created":"2023-06-10","cited_by_count":36},{"id":"2308.03135","title":"EventBind: Learning a Unified Representation to Bind Them All for Event-based Open-world Understanding","created":"2023-08-06","cited_by_count":34},{"id":"2403.12534","title":"ExACT: Language-guided Conceptual Reasoning and Uncertainty Estimation for Event-based Action Recognition and More","created":"2024-03-19","cited_by_count":33},{"id":"2412.00832","title":"EventGPT: Event Stream Understanding with Multimodal Large Language Models","created":"2024-12-01","cited_by_count":28},{"id":"2403.19976","title":"eTraM: Event-based Traffic Monitoring Dataset","created":"2024-03-29","cited_by_count":24},{"id":"2311.11533","title":"Event Camera Data Dense Pre-training","created":"2023-11-20","cited_by_count":21},{"id":"2405.17769","title":"Microsaccade-inspired Event Camera for Robotics","created":"2024-05-28","cited_by_count":17},{"id":"2407.05106","title":"DailyDVS-200: A Comprehensive Benchmark Dataset for Event-Based Action Recognition","created":"2024-07-06","cited_by_count":17},{"id":"2503.07298","title":"ALLVB: All-in-One Long Video Understanding Benchmark","created":"2025-03-10","cited_by_count":16},{"id":"2408.16254","title":"EvLight++: Low-Light Video Enhancement with an Event Camera: A Large-Scale Real-World Dataset, Novel Method, and More","created":"2024-08-29","cited_by_count":14},{"id":"2501.13707","title":"EventVL: Understand Event Streams via Multimodal Large Language Model","created":"2025-01-23","cited_by_count":13},{"id":"2308.16876","title":"SportsSloMo: A New Benchmark and Baselines for Human-centric Video Frame Interpolation","created":"2023-08-31","cited_by_count":11},{"id":"2203.03914","title":"Globally-Optimal Event Camera Motion Estimation","created":"2022-03-08","cited_by_count":10},{"id":"2407.21616","title":"EZSR: Event-based Zero-Shot Recognition","created":"2024-07-31","cited_by_count":8},{"id":"2510.00681","title":"Adaptive Event Stream Slicing for Open-Vocabulary Event-Based Object Detection via Vision-Language Knowledge Distillation","created":"2025-10-01","cited_by_count":8},{"id":"2311.18592","title":"Semantic-Aware Frame-Event Fusion based Pattern Recognition via Large Vision-Language Models","created":"2023-11-30","cited_by_count":7},{"id":"2504.12515","title":"Event Quality Score (EQS): Assessing the Realism of Simulated Event Camera Streams via Distances in Latent Space","created":"2025-04-16","cited_by_count":7},{"id":"2407.12593","title":"EvSign: Sign Language Recognition and Translation with Streaming Events","created":"2024-07-17","cited_by_count":6},{"id":"2507.17664","title":"Talk2Event: Grounded Understanding of Dynamic Scenes from Event Cameras","created":"2025-07-23","cited_by_count":6},{"id":"2503.06934","title":"LLaFEA: Frame-Event Complementary Fusion for Fine-Grained Spatiotemporal Understanding in LMMs","created":"2025-03-10","cited_by_count":5},{"id":"2506.07627","title":"Event-Priori-Based Vision-Language Model for Efficient Visual Understanding","created":"2025-06-09","cited_by_count":5},{"id":"2507.02200","title":"ESTR-CoT: Towards Explainable and Accurate Event Stream based Scene Text Recognition with Chain-of-Thought Reasoning","created":"2025-07-02","cited_by_count":3},{"id":"2508.07401","title":"LET-US: Long Event-Text Understanding of Scenes","created":"2025-08-10","cited_by_count":3},{"id":"2406.03439","title":"Text-to-Events: Synthetic Event Camera Streams from Conditional Text Input","created":"2024-06-05","cited_by_count":2},{"id":"2509.07525","title":"EHWGesture -- A dataset for multimodal understanding of clinical gestures","created":"2025-09-09","cited_by_count":2},{"id":"2509.22864","title":"ControlEvents: Controllable Synthesis of Event Camera Datawith Foundational Prior from Image Diffusion Models","created":"2025-09-26","cited_by_count":1}],"next_cursor":null}