{"list":"other","total":76,"rows":[{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"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":"2409.12191","title":"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution","created":"2024-09-18","cited_by_count":4234},{"id":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"id":"2511.21631","title":"Qwen3-VL Technical Report","created":"2025-11-26","cited_by_count":2793},{"id":"2408.03326","title":"LLaVA-OneVision: Easy Visual Task Transfer","created":"2024-08-06","cited_by_count":2719},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"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":"2306.14824","title":"Kosmos-2: Grounding Multimodal Large Language Models to the World","created":"2023-06-26","cited_by_count":1089},{"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":"1704.00675","title":"The 2017 DAVIS Challenge on Video Object Segmentation","created":"2017-04-03","cited_by_count":957},{"id":"2306.15195","title":"Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic","created":"2023-06-27","cited_by_count":906},{"id":"2305.06355","title":"VideoChat: Chat-Centric Video Understanding","created":"2023-05-10","cited_by_count":857},{"id":"1705.00754","title":"Dense-Captioning Events in Videos","created":"2017-05-02","cited_by_count":793},{"id":"2308.00692","title":"LISA: Reasoning Segmentation via Large Language Model","created":"2023-08-01","cited_by_count":776},{"id":"2406.07476","title":"VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs","created":"2024-06-11","cited_by_count":771},{"id":"2105.08276","title":"NExT-QA:Next Phase of Question-Answering to Explaining Temporal Actions","created":"2021-05-18","cited_by_count":744},{"id":"2311.03079","title":"CogVLM: Visual Expert for Pretrained Language Models","created":"2023-11-06","cited_by_count":708},{"id":"1708.01641","title":"Localizing Moments in Video with Natural Language","created":"2017-08-04","cited_by_count":663},{"id":"1703.09788","title":"Towards Automatic Learning of Procedures from Web Instructional Videos","created":"2017-03-28","cited_by_count":619},{"id":"1705.02101","title":"TALL: Temporal Activity Localization via Language Query","created":"2017-05-05","cited_by_count":584},{"id":"2501.13106","title":"VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding","created":"2025-01-22","cited_by_count":518},{"id":"2310.07704","title":"Ferret: Refer and Ground Anything Anywhere at Any Granularity","created":"2023-10-11","cited_by_count":509},{"id":"1910.01442","title":"CLEVRER: CoLlision Events for Video REpresentation and Reasoning","created":"2019-10-03","cited_by_count":484},{"id":"2406.04325","title":"ShareGPT4Video: Improving Video Understanding and Generation with Better Captions","created":"2024-06-06","cited_by_count":388},{"id":"1903.02874","title":"COIN: A Large-scale Dataset for Comprehensive Instructional Video Analysis","created":"2019-03-07","cited_by_count":318},{"id":"2305.13786","title":"Perception Test: A Diagnostic Benchmark for Multimodal Video Models","created":"2023-05-23","cited_by_count":314},{"id":"2307.03601","title":"GPT4RoI: Instruction Tuning Large Language Model on Region-of-Interest","created":"2023-07-07","cited_by_count":302},{"id":"2311.18445","title":"VTimeLLM: Empower LLM to Grasp Video Moments","created":"2023-11-30","cited_by_count":255},{"id":"2012.00451","title":"Just Ask: Learning to Answer Questions from Millions of Narrated Videos","created":"2020-12-01","cited_by_count":248},{"id":"2308.08544","title":"MeViS: A Large-scale Benchmark for Video Segmentation with Motion Expressions","created":"2023-08-16","cited_by_count":228},{"id":"2312.02228","title":"PixelLM: Pixel Reasoning with Large Multimodal Model","created":"2023-12-04","cited_by_count":222},{"id":"2405.09711","title":"STAR: A Benchmark for Situated Reasoning in Real-World Videos","created":"2024-05-15","cited_by_count":213},{"id":"2201.00487","title":"Language as Queries for Referring Video Object Segmentation","created":"2022-01-03","cited_by_count":182},{"id":"2312.10032","title":"Osprey: Pixel Understanding with Visual Instruction Tuning","created":"2023-12-15","cited_by_count":159},{"id":"2501.04001","title":"Sa2VA: Marrying SAM2 with MLLM for Dense Grounded Understanding of Images and Videos","created":"2025-01-07","cited_by_count":159},{"id":"2312.10103","title":"GSVA: Generalized Segmentation via Multimodal Large Language Models","created":"2023-12-15","cited_by_count":154},{"id":"2111.14821","title":"End-to-End Referring Video Object Segmentation with Multimodal Transformers","created":"2021-11-29","cited_by_count":135},{"id":"2309.01327","title":"Can I Trust Your Answer? Visually Grounded Video Question Answering","created":"2023-09-04","cited_by_count":135},{"id":"2407.11325","title":"VISA: Reasoning Video Object Segmentation via Large Language Models","created":"2024-07-16","cited_by_count":127},{"id":"2402.11435","title":"Momentor: Advancing Video Large Language Model with Fine-Grained Temporal Reasoning","created":"2024-02-18","cited_by_count":122},{"id":"2103.16002","title":"AGQA: A Benchmark for Compositional Spatio-Temporal Reasoning","created":"2021-03-30","cited_by_count":120},{"id":"2211.09552","title":"UniFormerV2: Spatiotemporal Learning by Arming Image ViTs with Video UniFormer","created":"2022-11-17","cited_by_count":116},{"id":"2308.07026","title":"AdvCLIP: Downstream-agnostic Adversarial Examples in Multimodal Contrastive Learning","created":"2023-08-14","cited_by_count":103},{"id":"2401.06071","title":"GroundingGPT:Language Enhanced Multi-modal Grounding Model","created":"2024-01-11","cited_by_count":101},{"id":"2409.19603","title":"One Token to Seg Them All: Language Instructed Reasoning Segmentation in Videos","created":"2024-09-29","cited_by_count":100},{"id":"2410.03290","title":"Grounded-VideoLLM: Sharpening Fine-grained Temporal Grounding in Video Large Language Models","created":"2024-10-04","cited_by_count":91},{"id":"2405.13382","title":"VTG-LLM: Integrating Timestamp Knowledge into Video LLMs for Enhanced Video Temporal Grounding","created":"2024-05-22","cited_by_count":85},{"id":"2504.16072","title":"Describe Anything: Detailed Localized Image and Video Captioning","created":"2025-04-22","cited_by_count":84},{"id":"2303.16406","title":"Hierarchical Video-Moment Retrieval and Step-Captioning","created":"2023-03-29","cited_by_count":83},{"id":"2502.11946","title":"Step-Audio: Unified Understanding and Generation in Intelligent Speech Interaction","created":"2025-02-17","cited_by_count":83},{"id":"2011.11760","title":"Multimodal Pretraining for Dense Video Captioning","created":"2020-11-10","cited_by_count":79},{"id":"2501.00599","title":"VideoRefer Suite: Advancing Spatial-Temporal Object Understanding with Video LLM","created":"2024-12-31","cited_by_count":72},{"id":"2409.18111","title":"E.T. Bench: Towards Open-Ended Event-Level Video-Language Understanding","created":"2024-09-26","cited_by_count":70},{"id":"2307.09356","title":"OnlineRefer: A Simple Online Baseline for Referring Video Object Segmentation","created":"2023-07-18","cited_by_count":62},{"id":"2311.06612","title":"PerceptionGPT: Effectively Fusing Visual Perception into LLM","created":"2023-11-11","cited_by_count":59},{"id":"2410.12813","title":"ChatVTG: Video Temporal Grounding via Chat with Video Dialogue Large Language Models","created":"2024-10-01","cited_by_count":54},{"id":"2506.05302","title":"Perceive Anything: Recognize, Explain, Caption, and Segment Anything in Images and Videos","created":"2025-06-05","cited_by_count":51},{"id":"2407.20242","title":"BadRobot: Jailbreaking Embodied LLM Agents in the Physical World","created":"2024-07-16","cited_by_count":43},{"id":"1804.09235","title":"On the effectiveness of task granularity for transfer learning","created":"2018-04-24","cited_by_count":35},{"id":"2504.07962","title":"GLUS: Global-Local Reasoning Unified into A Single Large Language Model for Video Segmentation","created":"2025-04-10","cited_by_count":34},{"id":"2411.17606","title":"HyperSeg: Towards Universal Visual Segmentation with Large Language Model","created":"2024-11-26","cited_by_count":33},{"id":"2409.17874","title":"DarkSAM: Fooling Segment Anything Model to Segment Nothing","created":"2024-09-26","cited_by_count":32},{"id":"2305.03347","title":"A Large Cross-Modal Video Retrieval Dataset with Reading Comprehension","created":"2023-05-05","cited_by_count":31},{"id":"2412.14006","title":"InstructSeg: Unifying Instructed Visual Segmentation with Multi-modal Large Language Models","created":"2024-12-18","cited_by_count":31},{"id":"2509.18094","title":"UniPixel: Unified Object Referring and Segmentation for Pixel-Level Visual Reasoning","created":"2025-09-22","cited_by_count":28},{"id":"2407.14500","title":"ViLLa: Video Reasoning Segmentation with Large Language Model","created":"2024-07-18","cited_by_count":24},{"id":"2509.16645","title":"ADVEDM:Fine-grained Adversarial Attack against VLM-based Embodied Agents","created":"2025-09-20","cited_by_count":23},{"id":"2402.00066","title":"TrackGPT -- A generative pre-trained transformer for cross-domain entity trajectory forecasting","created":"2024-01-29","cited_by_count":13},{"id":"2507.19599","title":"Object-centric Video Question Answering with Visual Grounding and Referring","created":"2025-07-25","cited_by_count":13},{"id":"2411.16932","title":"Seq2Time: Sequential Knowledge Transfer for Video LLM Temporal Grounding","created":"2024-11-25","cited_by_count":12},{"id":"2510.24195","title":"Vanish into Thin Air: Cross-prompt Universal Adversarial Attacks for SAM2","created":"2025-10-28","cited_by_count":11},{"id":"2505.24329","title":"DisTime: Distribution-based Time Representation for Video Large Language Models","created":"2025-05-30","cited_by_count":7}],"next_cursor":null}