{"list":"other","total":74,"rows":[{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"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":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"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":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2205.11916","title":"Large Language Models are Zero-Shot Reasoners","created":"2022-05-24","cited_by_count":4374},{"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":"2408.03314","title":"Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters","created":"2024-08-06","cited_by_count":1986},{"id":"2503.19786","title":"Gemma 3 Technical Report","created":"2025-03-25","cited_by_count":1824},{"id":"2303.17580","title":"HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face","created":"2023-03-30","cited_by_count":1190},{"id":"2306.14824","title":"Kosmos-2: Grounding Multimodal Large Language Models to the World","created":"2023-06-26","cited_by_count":1089},{"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":"2303.16199","title":"LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention","created":"2023-03-28","cited_by_count":781},{"id":"2210.03493","title":"Automatic Chain of Thought Prompting in Large Language Models","created":"2022-10-07","cited_by_count":688},{"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":"2310.07704","title":"Ferret: Refer and Ground Anything Anywhere at Any Granularity","created":"2023-10-11","cited_by_count":509},{"id":"2011.14503","title":"End-to-End Video Instance Segmentation with Transformers","created":"2020-11-30","cited_by_count":443},{"id":"2207.07115","title":"XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model","created":"2022-07-14","cited_by_count":439},{"id":"1904.00607","title":"Video Object Segmentation using Space-Time Memory Networks","created":"2019-04-01","cited_by_count":438},{"id":"2311.06242","title":"Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks","created":"2023-11-10","cited_by_count":410},{"id":"2301.13379","title":"Faithful Chain-of-Thought Reasoning","created":"2023-01-31","cited_by_count":288},{"id":"1812.05050","title":"Fast Online Object Tracking and Segmentation: A Unifying Approach","created":"2018-12-12","cited_by_count":272},{"id":"1904.04745","title":"Cross-Modal Self-Attention Network for Referring Image Segmentation","created":"2019-04-09","cited_by_count":263},{"id":"2305.13655","title":"LLM-grounded Diffusion: Enhancing Prompt Understanding of Text-to-Image Diffusion Models with Large Language Models","created":"2023-05-23","cited_by_count":243},{"id":"2108.05565","title":"Vision-Language Transformer and Query Generation for Referring Segmentation","created":"2021-08-12","cited_by_count":240},{"id":"1611.05198","title":"One-Shot Video Object Segmentation","created":"2016-11-16","cited_by_count":235},{"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":"2106.05210","title":"Rethinking Space-Time Networks with Improved Memory Coverage for Efficient Video Object Segmentation","created":"2021-06-09","cited_by_count":203},{"id":"2310.12982","title":"Putting the Object Back into Video Object Segmentation","created":"2023-10-19","cited_by_count":188},{"id":"2201.00487","title":"Language as Queries for Referring Video Object Segmentation","created":"2022-01-03","cited_by_count":182},{"id":"1902.09513","title":"FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation","created":"2019-02-25","cited_by_count":178},{"id":"2112.10764","title":"Mask2Former for Video Instance Segmentation","created":"2021-12-20","cited_by_count":171},{"id":"2311.17842","title":"Look Before You Leap: Unveiling the Power of GPT-4V in Robotic Vision-Language Planning","created":"2023-11-29","cited_by_count":161},{"id":"2312.10103","title":"GSVA: Generalized Segmentation via Multimodal Large Language Models","created":"2023-12-15","cited_by_count":154},{"id":"1612.02646","title":"Learning Video Object Segmentation from Static Images","created":"2016-12-08","cited_by_count":151},{"id":"2003.08333","title":"Collaborative Video Object Segmentation by Foreground-Background Integration","created":"2020-03-18","cited_by_count":142},{"id":"2111.14821","title":"End-to-End Referring Video Object Segmentation with Multimodal Transformers","created":"2021-11-29","cited_by_count":135},{"id":"2301.13823","title":"Grounding Language Models to Images for Multimodal Inputs and Outputs","created":"2023-01-31","cited_by_count":131},{"id":"2404.13013","title":"Groma: Localized Visual Tokenization for Grounding Multimodal Large Language Models","created":"2024-04-19","cited_by_count":119},{"id":"2305.18279","title":"Contextual Object Detection with Multimodal Large Language Models","created":"2023-05-29","cited_by_count":100},{"id":"2112.08275","title":"SeqFormer: Sequential Transformer for Video Instance Segmentation","created":"2021-12-15","cited_by_count":98},{"id":"2305.05662","title":"InternGPT: Solving Vision-Centric Tasks by Interacting with ChatGPT Beyond Language","created":"2023-05-09","cited_by_count":96},{"id":"1709.06031","title":"Video Object Segmentation Without Temporal Information","created":"2017-09-18","cited_by_count":93},{"id":"1809.01123","title":"VideoMatch: Matching based Video Object Segmentation","created":"2018-09-04","cited_by_count":90},{"id":"2003.11540","title":"Learning What to Learn for Video Object Segmentation","created":"2020-03-25","cited_by_count":89},{"id":"2307.01197","title":"Segment Anything Meets Point Tracking","created":"2023-07-03","cited_by_count":81},{"id":"2311.04498","title":"NExT-Chat: An LMM for Chat, Detection and Segmentation","created":"2023-11-08","cited_by_count":80},{"id":"2306.03413","title":"DVIS: Decoupled Video Instance Segmentation Framework","created":"2023-06-06","cited_by_count":77},{"id":"2003.00908","title":"Learning Fast and Robust Target Models for Video Object Segmentation","created":"2020-02-27","cited_by_count":76},{"id":"1804.03131","title":"Blazingly Fast Video Object Segmentation with Pixel-Wise Metric Learning","created":"2018-04-09","cited_by_count":74},{"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":"2307.09356","title":"OnlineRefer: A Simple Online Baseline for Referring Video Object Segmentation","created":"2023-07-18","cited_by_count":62},{"id":"1806.02323","title":"Fast and Accurate Online Video Object Segmentation via Tracking Parts","created":"2018-06-06","cited_by_count":57},{"id":"2305.17011","title":"SOC: Semantic-Assisted Object Cluster for Referring Video Object Segmentation","created":"2023-05-26","cited_by_count":57},{"id":"2003.00482","title":"State-Aware Tracker for Real-Time Video Object Segmentation","created":"2020-03-01","cited_by_count":54},{"id":"2311.13435","title":"PG-Video-LLaVA: Pixel Grounding Large Video-Language Models","created":"2023-11-22","cited_by_count":51},{"id":"2206.03789","title":"Language-Bridged Spatial-Temporal Interaction for Referring Video Object Segmentation","created":"2022-06-08","cited_by_count":50},{"id":"2207.01203","title":"Towards Robust Referring Video Object Segmentation with Cyclic Relational Consensus","created":"2022-07-04","cited_by_count":50},{"id":"1803.09453","title":"CNN in MRF: Video Object Segmentation via Inference in A CNN-Based Higher-Order Spatio-Temporal MRF","created":"2018-03-26","cited_by_count":48},{"id":"2307.13537","title":"Spectrum-guided Multi-granularity Referring Video Object Segmentation","created":"2023-07-25","cited_by_count":48},{"id":"2403.16558","title":"Elysium: Exploring Object-level Perception in Videos via MLLM","created":"2024-03-25","cited_by_count":48},{"id":"2312.13305","title":"DVIS++: Improved Decoupled Framework for Universal Video Segmentation","created":"2023-12-20","cited_by_count":46},{"id":"2411.17646","title":"SAMWISE: Infusing Wisdom in SAM2 for Text-Driven Video Segmentation","created":"2024-11-26","cited_by_count":44},{"id":"2403.02969","title":"Multi-modal Instruction Tuned LLMs with Fine-grained Visual Perception","created":"2024-03-05","cited_by_count":39},{"id":"1910.00132","title":"CapsuleVOS: Semi-Supervised Video Object Segmentation Using Capsule Routing","created":"2019-09-30","cited_by_count":29},{"id":"1904.02363","title":"Spatiotemporal CNN for Video Object Segmentation","created":"2019-04-04","cited_by_count":24},{"id":"2404.00086","title":"DVIS-DAQ: Improving Video Segmentation via Dynamic Anchor Queries","created":"2024-03-29","cited_by_count":22},{"id":"1907.08895","title":"An Efficient 3D CNN for Action/Object Segmentation in Video","created":"2019-07-21","cited_by_count":10},{"id":"2101.06545","title":"VideoClick: Video Object Segmentation with a Single Click","created":"2021-01-16","cited_by_count":8}],"next_cursor":null}