{"list":"other","total":62,"rows":[{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"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":"2309.16609","title":"Qwen Technical Report","created":"2023-09-28","cited_by_count":3344},{"id":"2303.05499","title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","created":"2023-03-09","cited_by_count":3332},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1612.00837","title":"Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering","created":"2016-12-02","cited_by_count":2516},{"id":"2308.12966","title":"Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond","created":"2023-08-24","cited_by_count":2224},{"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":"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":"1505.04870","title":"Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models","created":"2015-05-19","cited_by_count":1362},{"id":"2112.03857","title":"Grounded Language-Image Pre-training","created":"2021-12-07","cited_by_count":1156},{"id":"2311.17005","title":"MVBench: A Comprehensive Multi-modal Video Understanding Benchmark","created":"2023-11-28","cited_by_count":1109},{"id":"1406.2199","title":"Two-Stream Convolutional Networks for Action Recognition in Videos","created":"2014-06-09","cited_by_count":1068},{"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":"2306.15195","title":"Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic","created":"2023-06-27","cited_by_count":906},{"id":"2311.03079","title":"CogVLM: Visual Expert for Pretrained Language Models","created":"2023-11-06","cited_by_count":708},{"id":"2308.09126","title":"EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding","created":"2023-08-17","cited_by_count":680},{"id":"1708.01641","title":"Localizing Moments in Video with Natural Language","created":"2017-08-04","cited_by_count":663},{"id":"2310.09478","title":"MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning","created":"2023-10-14","cited_by_count":625},{"id":"1705.02101","title":"TALL: Temporal Activity Localization via Language Query","created":"2017-05-05","cited_by_count":584},{"id":"1811.10830","title":"From Recognition to Cognition: Visual Commonsense Reasoning","created":"2018-11-27","cited_by_count":556},{"id":"2310.07704","title":"Ferret: Refer and Ground Anything Anywhere at Any Granularity","created":"2023-10-11","cited_by_count":509},{"id":"2011.10678","title":"Open-Vocabulary Object Detection Using Captions","created":"2020-11-20","cited_by_count":427},{"id":"2404.18930","title":"Hallucination of Multimodal Large Language Models: A Survey","created":"2024-04-29","cited_by_count":388},{"id":"1711.07319","title":"Cascaded Pyramid Network for Multi-Person Pose Estimation","created":"2017-11-20","cited_by_count":341},{"id":"2311.07575","title":"SPHINX: The Joint Mixing of Weights, Tasks, and Visual Embeddings for Multi-modal Large Language Models","created":"2023-11-13","cited_by_count":286},{"id":"2307.09009","title":"How is ChatGPT's behavior changing over time?","created":"2023-07-18","cited_by_count":270},{"id":"2302.01872","title":"MOSE: A New Dataset for Video Object Segmentation in Complex Scenes","created":"2023-02-03","cited_by_count":234},{"id":"2308.08544","title":"MeViS: A Large-scale Benchmark for Video Segmentation with Motion Expressions","created":"2023-08-16","cited_by_count":228},{"id":"2501.12380","title":"MMVU: Measuring Expert-Level Multi-Discipline Video Understanding","created":"2025-01-21","cited_by_count":137},{"id":"2001.06891","title":"Where Does It Exist: Spatio-Temporal Video Grounding for Multi-Form Sentences","created":"2020-01-19","cited_by_count":118},{"id":"2312.02949","title":"LLaVA-Grounding: Grounded Visual Chat with Large Multimodal Models","created":"2023-12-05","cited_by_count":113},{"id":"2203.16434","title":"TubeDETR: Spatio-Temporal Video Grounding with Transformers","created":"2022-03-30","cited_by_count":98},{"id":"2011.05049","title":"Human-centric Spatio-Temporal Video Grounding With Visual Transformers","created":"2020-11-10","cited_by_count":85},{"id":"2207.00419","title":"Self-Supervised Learning for Videos: A Survey","created":"2022-06-18","cited_by_count":85},{"id":"2501.00599","title":"VideoRefer Suite: Advancing Spatial-Temporal Object Understanding with Video LLM","created":"2024-12-31","cited_by_count":72},{"id":"2508.05630","title":"MOSEv2: A More Challenging Dataset for Video Object Segmentation in Complex Scenes","created":"2025-08-07","cited_by_count":62},{"id":"2405.03770","title":"Foundation Models for Video Understanding: A Survey","created":"2024-05-06","cited_by_count":46},{"id":"2209.13306","title":"Embracing Consistency: A One-Stage Approach for Spatio-Temporal Video Grounding","created":"2022-09-27","cited_by_count":42},{"id":"2307.12813","title":"Described Object Detection: Liberating Object Detection with Flexible Expressions","created":"2023-07-24","cited_by_count":40},{"id":"2410.12332","title":"MC-Bench: A Benchmark for Multi-Context Visual Grounding in the Era of MLLMs","created":"2024-10-16","cited_by_count":39},{"id":"2512.10945","title":"MeViS: A Multi-Modal Dataset for Referring Motion Expression Video Segmentation","created":"2025-12-11","cited_by_count":35},{"id":"2207.02159","title":"Robustness Analysis of Video-Language Models Against Visual and Language Perturbations","created":"2022-07-05","cited_by_count":23},{"id":"2505.14321","title":"Breaking Down Video LLM Benchmarks: Knowledge, Spatial Perception, or True Temporal Understanding?","created":"2025-05-20","cited_by_count":20},{"id":"2603.08620","title":"StreamReady: Learning What to Answer and When in Long Streaming Videos","created":"2026-03-09","cited_by_count":19},{"id":"2503.08585","title":"HierarQ: Task-Aware Hierarchical Q-Former for Enhanced Video Understanding","created":"2025-03-11","cited_by_count":17},{"id":"2304.13700","title":"UniNeXt: Exploring A Unified Architecture for Vision Recognition","created":"2023-04-26","cited_by_count":16},{"id":"2506.05336","title":"VideoMolmo: Spatio-Temporal Grounding Meets Pointing","created":"2025-06-05","cited_by_count":14},{"id":"2204.07892","title":"Video Action Detection: Analysing Limitations and Challenges","created":"2022-04-17","cited_by_count":12},{"id":"2411.16793","title":"ST-Align: A Multimodal Foundation Model for Image-Gene Alignment in Spatial Transcriptomics","created":"2024-11-25","cited_by_count":12},{"id":"2502.20678","title":"STPro: Spatial and Temporal Progressive Learning for Weakly Supervised Spatio-Temporal Grounding","created":"2025-02-28","cited_by_count":11},{"id":"2312.07169","title":"Semi-supervised Active Learning for Video Action Detection","created":"2023-12-12","cited_by_count":10},{"id":"2501.17053","title":"Contextual Self-paced Learning for Weakly Supervised Spatio-Temporal Video Grounding","created":"2025-01-28","cited_by_count":10},{"id":"2410.19553","title":"On Occlusions in Video Action Detection: Benchmark Datasets And Training Recipes","created":"2024-10-25","cited_by_count":6},{"id":"2412.07072","title":"Stable Mean Teacher for Semi-supervised Video Action Detection","created":"2024-12-10","cited_by_count":6},{"id":"2402.19405","title":"Navigating Hallucinations for Reasoning of Unintentional Activities","created":"2024-02-29","cited_by_count":3},{"id":"2508.13983","title":"OmViD: Omni-supervised active learning for video action detection","created":"2025-08-19","cited_by_count":3},{"id":"2510.13016","title":"SVAG-Bench: A Large-Scale Benchmark for Multi-Instance Spatio-temporal Video Action Grounding","created":"2025-10-14","cited_by_count":3}],"next_cursor":null}