{"list":"other","total":94,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"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":"2309.16609","title":"Qwen Technical Report","created":"2023-09-28","cited_by_count":3344},{"id":"2305.06500","title":"InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning","created":"2023-05-11","cited_by_count":2876},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"id":"2408.03326","title":"LLaVA-OneVision: Easy Visual Task Transfer","created":"2024-08-06","cited_by_count":2719},{"id":"2312.14238","title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","created":"2023-12-21","cited_by_count":2565},{"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":"2003.04297","title":"Improved Baselines with Momentum Contrastive Learning","created":"2020-03-09","cited_by_count":2287},{"id":"2407.10671","title":"Qwen2 Technical Report","created":"2024-07-15","cited_by_count":2120},{"id":"2311.16502","title":"MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI","created":"2023-11-27","cited_by_count":2080},{"id":"2404.14219","title":"Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone","created":"2024-04-22","cited_by_count":1917},{"id":"2305.10355","title":"Evaluating Object Hallucination in Large Vision-Language Models","created":"2023-05-17","cited_by_count":1729},{"id":"1904.08920","title":"Towards VQA Models That Can Read","created":"2019-04-18","cited_by_count":1718},{"id":"2306.13394","title":"MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models","created":"2023-06-23","cited_by_count":1652},{"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":"2311.10122","title":"Video-LLaVA: Learning United Visual Representation by Alignment Before Projection","created":"2023-11-16","cited_by_count":1402},{"id":"1805.04687","title":"BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning","created":"2018-05-12","cited_by_count":1288},{"id":"2308.02490","title":"MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities","created":"2023-08-04","cited_by_count":1239},{"id":"2305.10403","title":"PaLM 2 Technical Report","created":"2023-05-17","cited_by_count":1162},{"id":"2408.01800","title":"MiniCPM-V: A GPT-4V Level MLLM on Your Phone","created":"2024-08-03","cited_by_count":1079},{"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":"2311.12793","title":"ShareGPT4V: Improving Large Multi-Modal Models with Better Captions","created":"2023-11-21","cited_by_count":1005},{"id":"2405.09818","title":"Chameleon: Mixed-Modal Early-Fusion Foundation Models","created":"2024-05-16","cited_by_count":927},{"id":"2403.20330","title":"Are We on the Right Way for Evaluating Large Vision-Language Models?","created":"2024-03-29","cited_by_count":914},{"id":"2406.16860","title":"Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs","created":"2024-06-24","cited_by_count":838},{"id":"2401.06209","title":"Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs","created":"2024-01-11","cited_by_count":735},{"id":"2403.05525","title":"DeepSeek-VL: Towards Real-World Vision-Language Understanding","created":"2024-03-08","cited_by_count":733},{"id":"2403.04652","title":"Yi: Open Foundation Models by 01.AI","created":"2024-03-07","cited_by_count":719},{"id":"2301.00808","title":"ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders","created":"2023-01-02","cited_by_count":712},{"id":"2312.07533","title":"VILA: On Pre-training for Visual Language Models","created":"2023-12-12","cited_by_count":692},{"id":"2407.07895","title":"LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models","created":"2024-07-10","cited_by_count":584},{"id":"2404.12390","title":"BLINK: Multimodal Large Language Models Can See but Not Perceive","created":"2024-04-18","cited_by_count":550},{"id":"2311.17043","title":"LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models","created":"2023-11-28","cited_by_count":546},{"id":"2307.16449","title":"MovieChat: From Dense Token to Sparse Memory for Long Video Understanding","created":"2023-07-31","cited_by_count":542},{"id":"1603.00831","title":"MOT16: A Benchmark for Multi-Object Tracking","created":"2016-03-02","cited_by_count":532},{"id":"2311.03356","title":"GLaMM: Pixel Grounding Large Multimodal Model","created":"2023-11-06","cited_by_count":455},{"id":"1809.07845","title":"LaSOT: A High-quality Benchmark for Large-scale Single Object Tracking","created":"2018-09-20","cited_by_count":429},{"id":"1905.04804","title":"Video Instance Segmentation","created":"2019-05-12","cited_by_count":393},{"id":"2403.18814","title":"Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models","created":"2024-03-27","cited_by_count":365},{"id":"2311.06607","title":"Monkey: Image Resolution and Text Label Are Important Things for Large Multi-modal Models","created":"2023-11-11","cited_by_count":357},{"id":"2308.16911","title":"PointLLM: Empowering Large Language Models to Understand Point Clouds","created":"2023-08-31","cited_by_count":333},{"id":"2306.16527","title":"OBELICS: An Open Web-Scale Filtered Dataset of Interleaved Image-Text Documents","created":"2023-06-21","cited_by_count":316},{"id":"2408.04840","title":"mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Models","created":"2024-08-09","cited_by_count":291},{"id":"2302.01872","title":"MOSE: A New Dataset for Video Object Segmentation in Complex Scenes","created":"2023-02-03","cited_by_count":234},{"id":"2212.04501","title":"Learning Video Representations from Large Language Models","created":"2022-12-08","cited_by_count":205},{"id":"2303.06674","title":"Universal Instance Perception as Object Discovery and Retrieval","created":"2023-03-12","cited_by_count":192},{"id":"2408.05211","title":"VITA: Towards Open-Source Interactive Omni Multimodal LLM","created":"2024-08-09","cited_by_count":173},{"id":"2312.06709","title":"AM-RADIO: Agglomerative Vision Foundation Model -- Reduce All Domains Into One","created":"2023-12-10","cited_by_count":169},{"id":"2405.20797","title":"Ovis: Structural Embedding Alignment for Multimodal Large Language Model","created":"2024-05-31","cited_by_count":169},{"id":"2312.00784","title":"ViP-LLaVA: Making Large Multimodal Models Understand Arbitrary Visual Prompts","created":"2023-12-01","cited_by_count":161},{"id":"2312.10032","title":"Osprey: Pixel Understanding with Visual Instruction Tuning","created":"2023-12-15","cited_by_count":159},{"id":"2102.01558","title":"Occluded Video Instance Segmentation: A Benchmark","created":"2021-02-02","cited_by_count":154},{"id":"2408.15998","title":"Eagle: Exploring The Design Space for Multimodal LLMs with Mixture of Encoders","created":"2024-08-28","cited_by_count":139},{"id":"2304.05170","title":"SportsMOT: A Large Multi-Object Tracking Dataset in Multiple Sports Scenes","created":"2023-04-11","cited_by_count":131},{"id":"2308.08769","title":"Chat-3D: Data-efficiently Tuning Large Language Model for Universal Dialogue of 3D Scenes","created":"2023-08-17","cited_by_count":129},{"id":"2403.20271","title":"Draw-and-Understand: Leveraging Visual Prompts to Enable MLLMs to Comprehend What You Want","created":"2024-03-29","cited_by_count":101},{"id":"2207.10661","title":"In Defense of Online Models for Video Instance Segmentation","created":"2022-07-21","cited_by_count":97},{"id":"2410.14669","title":"NaturalBench: Evaluating Vision-Language Models on Natural Adversarial Samples","created":"2024-10-18","cited_by_count":97},{"id":"2207.07078","title":"Towards Grand Unification of Object Tracking","created":"2022-07-14","cited_by_count":93},{"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":"2310.19773","title":"MM-VID: Advancing Video Understanding with GPT-4V(ision)","created":"2023-10-30","cited_by_count":83},{"id":"2204.04656","title":"Video K-Net: A Simple, Strong, and Unified Baseline for Video Segmentation","created":"2022-04-10","cited_by_count":79},{"id":"2306.03413","title":"DVIS: Decoupled Video Instance Segmentation Framework","created":"2023-06-06","cited_by_count":77},{"id":"2406.08487","title":"Beyond LLaVA-HD: Diving into High-Resolution Large Multimodal Models","created":"2024-06-12","cited_by_count":76},{"id":"2401.10229","title":"OMG-Seg: Is One Model Good Enough For All Segmentation?","created":"2024-01-18","cited_by_count":75},{"id":"2501.00599","title":"VideoRefer Suite: Advancing Spatial-Temporal Object Understanding with Video LLM","created":"2024-12-31","cited_by_count":72},{"id":"2007.07247","title":"Multiview Detection with Feature Perspective Transformation","created":"2020-07-14","cited_by_count":71},{"id":"2408.02718","title":"MMIU: Multimodal Multi-image Understanding for Evaluating Large Vision-Language Models","created":"2024-08-05","cited_by_count":67},{"id":"2209.12118","title":"BURST: A Benchmark for Unifying Object Recognition, Segmentation and Tracking in Video","created":"2022-09-25","cited_by_count":66},{"id":"1803.09502","title":"Long-term Tracking in the Wild: A Benchmark","created":"2018-03-26","cited_by_count":55},{"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":"2307.12616","title":"CTVIS: Consistent Training for Online Video Instance Segmentation","created":"2023-07-24","cited_by_count":51},{"id":"2406.04221","title":"Matching Anything by Segmenting Anything","created":"2024-06-06","cited_by_count":50},{"id":"2312.13305","title":"DVIS++: Improved Decoupled Framework for Universal Video Segmentation","created":"2023-12-20","cited_by_count":46},{"id":"2407.21534","title":"ControlMLLM: Training-Free Visual Prompt Learning for Multimodal Large Language Models","created":"2024-07-31","cited_by_count":33},{"id":"2403.03493","title":"VastTrack: Vast Category Visual Object Tracking","created":"2024-03-06","cited_by_count":26},{"id":"2303.12782","title":"Tube-Link: A Flexible Cross Tube Framework for Universal Video Segmentation","created":"2023-03-22","cited_by_count":23},{"id":"2404.00086","title":"DVIS-DAQ: Improving Video Segmentation via Dynamic Anchor Queries","created":"2024-03-29","cited_by_count":22},{"id":"2202.13073","title":"Global Instance Tracking: Locating Target More Like Humans","created":"2022-02-26","cited_by_count":18},{"id":"1707.09299","title":"The WILDTRACK Multi-Camera Person Dataset","created":"2017-07-28","cited_by_count":10},{"id":"2306.04091","title":"1st Place Solution for PVUW Challenge 2023: Video Panoptic Segmentation","created":"2023-06-07","cited_by_count":7},{"id":"2308.14392","title":"1st Place Solution for the 5th LSVOS Challenge: Video Instance Segmentation","created":"2023-08-28","cited_by_count":6},{"id":"2402.11297","title":"MMMModal -- Multi-Images Multi-Audio Multi-turn Multi-Modal","created":"2024-02-17","cited_by_count":2}],"next_cursor":null}