{"list":"other","total":81,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"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":"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":"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":"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":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"2503.11651","title":"VGGT: Visual Geometry Grounded Transformer","created":"2025-03-14","cited_by_count":1539},{"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":"2403.13372","title":"LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models","created":"2024-03-20","cited_by_count":1464},{"id":"2406.09414","title":"Depth Anything V2","created":"2024-06-13","cited_by_count":1422},{"id":"2401.10891","title":"Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data","created":"2024-01-19","cited_by_count":1360},{"id":"1710.03077","title":"Deeper, Broader and Artier Domain Generalization","created":"2017-10-09","cited_by_count":986},{"id":"1511.07247","title":"NetVLAD: CNN architecture for weakly supervised place recognition","created":"2015-11-23","cited_by_count":941},{"id":"2103.02503","title":"Domain Generalization: A Survey","created":"2021-03-03","cited_by_count":764},{"id":"2401.12168","title":"SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities","created":"2024-01-22","cited_by_count":706},{"id":"2308.09126","title":"EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding","created":"2023-08-17","cited_by_count":680},{"id":"2104.02008","title":"Domain Generalization with MixStyle","created":"2021-04-05","cited_by_count":566},{"id":"2311.18259","title":"Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives","created":"2023-11-30","cited_by_count":490},{"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":"2305.14836","title":"NuScenes-QA: A Multi-modal Visual Question Answering Benchmark for Autonomous Driving Scenario","created":"2023-05-24","cited_by_count":262},{"id":"2005.00343","title":"The EPIC-KITCHENS Dataset: Collection, Challenges and Baselines","created":"2020-04-29","cited_by_count":225},{"id":"2410.24221","title":"EgoMimic: Scaling Imitation Learning via Egocentric Video","created":"2024-10-31","cited_by_count":175},{"id":"2307.15058","title":"MARS: An Instance-aware, Modular and Realistic Simulator for Autonomous Driving","created":"2023-07-27","cited_by_count":170},{"id":"2507.11539","title":"Streaming 4D Visual Geometry Transformer","created":"2025-07-15","cited_by_count":161},{"id":"2306.09310","title":"Infinite Photorealistic Worlds using Procedural Generation","created":"2023-06-15","cited_by_count":147},{"id":"2307.05463","title":"EgoVLPv2: Egocentric Video-Language Pre-training with Fusion in the Backbone","created":"2023-07-11","cited_by_count":130},{"id":"2210.03929","title":"EgoTaskQA: Understanding Human Tasks in Egocentric Videos","created":"2022-10-08","cited_by_count":115},{"id":"2411.04998","title":"HourVideo: 1-Hour Video-Language Understanding","created":"2024-11-07","cited_by_count":113},{"id":"2106.05969","title":"Dynamics-Regulated Kinematic Policy for Egocentric Pose Estimation","created":"2021-06-10","cited_by_count":101},{"id":"2403.16182","title":"EgoExoLearn: A Dataset for Bridging Asynchronous Ego- and Exo-centric View of Procedural Activities in Real World","created":"2024-03-24","cited_by_count":95},{"id":"2212.00259","title":"Super-CLEVR: A Virtual Benchmark to Diagnose Domain Robustness in Visual Reasoning","created":"2022-12-01","cited_by_count":92},{"id":"2503.03803","title":"EgoLife: Towards Egocentric Life Assistant","created":"2025-03-05","cited_by_count":91},{"id":"2403.09637","title":"GaussianGrasper: 3D Language Gaussian Splatting for Open-vocabulary Robotic Grasping","created":"2024-03-14","cited_by_count":78},{"id":"2503.16591","title":"UniK3D: Universal Camera Monocular 3D Estimation","created":"2025-03-20","cited_by_count":62},{"id":"2311.15596","title":"EgoThink: Evaluating First-Person Perspective Thinking Capability of Vision-Language Models","created":"2023-11-27","cited_by_count":60},{"id":"1811.10698","title":"LSTA: Long Short-Term Attention for Egocentric Action Recognition","created":"2018-11-26","cited_by_count":57},{"id":"2302.09309","title":"StyleAdv: Meta Style Adversarial Training for Cross-Domain Few-Shot Learning","created":"2023-02-18","cited_by_count":53},{"id":"1912.10405","title":"Adversarial Cross-Domain Action Recognition with Co-Attention","created":"2019-12-22","cited_by_count":51},{"id":"2010.09982","title":"Depth Guided Adaptive Meta-Fusion Network for Few-shot Video Recognition","created":"2020-10-20","cited_by_count":50},{"id":"2403.12532","title":"UniBind: LLM-Augmented Unified and Balanced Representation Space to Bind Them All","created":"2024-03-19","cited_by_count":49},{"id":"2107.11978","title":"Meta-FDMixup: Cross-Domain Few-Shot Learning Guided by Labeled Target Data","created":"2021-07-26","cited_by_count":48},{"id":"2303.14360","title":"Both Style and Distortion Matter: Dual-Path Unsupervised Domain Adaptation for Panoramic Semantic Segmentation","created":"2023-03-25","cited_by_count":47},{"id":"2401.01578","title":"Context-Guided Spatio-Temporal Video Grounding","created":"2024-01-03","cited_by_count":46},{"id":"2505.12448","title":"SSR: Enhancing Depth Perception in Vision-Language Models via Rationale-Guided Spatial Reasoning","created":"2025-05-18","cited_by_count":46},{"id":"2503.13646","title":"Omnia de EgoTempo: Benchmarking Temporal Understanding of Multi-Modal LLMs in Egocentric Videos","created":"2025-03-17","cited_by_count":44},{"id":"2402.03094","title":"Cross-Domain Few-Shot Object Detection via Enhanced Open-Set Object Detector","created":"2024-02-05","cited_by_count":43},{"id":"2210.15176","title":"Domain Adaptive Object Detection for Autonomous Driving under Foggy Weather","created":"2022-10-27","cited_by_count":41},{"id":"2501.02464","title":"Depth Any Camera: Zero-Shot Metric Depth Estimation from Any Camera","created":"2025-01-05","cited_by_count":40},{"id":"2308.05493","title":"Look at the Neighbor: Distortion-aware Unsupervised Domain Adaptation for Panoramic Semantic Segmentation","created":"2023-08-10","cited_by_count":38},{"id":"2308.03063","title":"M$^3$Net: Multi-view Encoding, Matching, and Fusion for Few-shot Fine-grained Action Recognition","created":"2023-08-06","cited_by_count":34},{"id":"2410.10791","title":"CAFuser: Condition-Aware Multimodal Fusion for Robust Semantic Perception of Driving Scenes","created":"2024-10-14","cited_by_count":33},{"id":"2404.00469","title":"SceneGraphLoc: Cross-Modal Coarse Visual Localization on 3D Scene Graphs","created":"2024-03-30","cited_by_count":29},{"id":"2503.09143","title":"Exo2Ego: Exocentric Knowledge Guided MLLM for Egocentric Video Understanding","created":"2025-03-12","cited_by_count":25},{"id":"2504.04517","title":"Enhance Then Search: An Augmentation-Search Strategy with Foundation Models for Cross-Domain Few-Shot Object Detection","created":"2025-04-06","cited_by_count":24},{"id":"2203.07656","title":"Wave-SAN: Wavelet based Style Augmentation Network for Cross-Domain Few-Shot Learning","created":"2022-03-15","cited_by_count":23},{"id":"2505.11907","title":"Are Multimodal Large Language Models Ready for Omnidirectional Spatial Reasoning?","created":"2025-05-17","cited_by_count":23},{"id":"2503.08221","title":"EgoBlind: Towards Egocentric Visual Assistance for the Blind","created":"2025-03-11","cited_by_count":21},{"id":"2508.10729","title":"EgoCross: Benchmarking Multimodal Large Language Models for Cross-Domain Egocentric Video Question Answering","created":"2025-08-14","cited_by_count":21},{"id":"2107.03120","title":"Cross-View Exocentric to Egocentric Video Synthesis","created":"2021-07-07","cited_by_count":20},{"id":"2505.22246","title":"StateSpaceDiffuser: Bringing Long Context to Diffusion World Models","created":"2025-05-28","cited_by_count":19},{"id":"2308.10239","title":"From Global to Local: Multi-scale Out-of-distribution Detection","created":"2023-08-20","cited_by_count":18},{"id":"2210.05392","title":"TGDM: Target Guided Dynamic Mixup for Cross-Domain Few-Shot Learning","created":"2022-10-11","cited_by_count":16},{"id":"2407.01872","title":"Referring Atomic Video Action Recognition","created":"2024-07-02","cited_by_count":16},{"id":"2506.05872","title":"Domain-RAG: Retrieval-Guided Compositional Image Generation for Cross-Domain Few-Shot Object Detection","created":"2025-06-06","cited_by_count":15},{"id":"2404.14967","title":"CoARF: Controllable 3D Artistic Style Transfer for Radiance Fields","created":"2024-04-23","cited_by_count":14},{"id":"2506.17629","title":"CLiViS: Unleashing Cognitive Map through Linguistic-Visual Synergy for Embodied Visual Reasoning","created":"2025-06-21","cited_by_count":13},{"id":"2409.17555","title":"Advancing Open-Set Domain Generalization Using Evidential Bi-Level Hardest Domain Scheduler","created":"2024-09-26","cited_by_count":12},{"id":"2412.00767","title":"Prompt as Free Lunch: Enhancing Diversity in Source-Free Cross-domain Few-shot Learning through Semantic-Guided Prompting","created":"2024-12-01","cited_by_count":10},{"id":"2210.05280","title":"ME-D2N: Multi-Expert Domain Decompositional Network for Cross-Domain Few-Shot Learning","created":"2022-10-11","cited_by_count":9},{"id":"2506.04224","title":"Seeing in the Dark: Benchmarking Egocentric 3D Vision with the Oxford Day-and-Night Dataset","created":"2025-06-04","cited_by_count":8},{"id":"2509.15237","title":"MICA: Multi-Agent Industrial Coordination Assistant","created":"2025-09-17","cited_by_count":8},{"id":"2209.14072","title":"City-scale Incremental Neural Mapping with Three-layer Sampling and Panoptic Representation","created":"2022-09-28","cited_by_count":7},{"id":"2310.03375","title":"Point-Based Radiance Fields for Controllable Human Motion Synthesis","created":"2023-10-05","cited_by_count":7},{"id":"2011.14478","title":"Annotation-Efficient Untrimmed Video Action Recognition","created":"2020-11-30","cited_by_count":6},{"id":"2211.10567","title":"CL-CrossVQA: A Continual Learning Benchmark for Cross-Domain Visual Question Answering","created":"2022-11-19","cited_by_count":6},{"id":"2412.18342","title":"Mitigating Label Noise using Prompt-Based Hyperbolic Meta-Learning in Open-Set Domain Generalization","created":"2024-12-24","cited_by_count":6},{"id":"2311.00807","title":"VQA-GEN: A Visual Question Answering Benchmark for Domain Generalization","created":"2023-11-01","cited_by_count":5},{"id":"2306.02393","title":"EgoSpot:Egocentric Multimodal Control for Hands-Free Mobile Manipulation","created":"2023-06-04","cited_by_count":3},{"id":"2409.20140","title":"RISE-SDF: a Relightable Information-Shared Signed Distance Field for Glossy Object Inverse Rendering","created":"2024-09-30","cited_by_count":3}],"next_cursor":null}