{"list":"other","total":55,"rows":[{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351},{"id":"1904.01201","title":"Habitat: A Platform for Embodied AI Research","created":"2019-04-02","cited_by_count":1191},{"id":"1704.00675","title":"The 2017 DAVIS Challenge on Video Object Segmentation","created":"2017-04-03","cited_by_count":957},{"id":"2202.09368","title":"Mixture-of-Experts with Expert Choice Routing","created":"2022-02-18","cited_by_count":623},{"id":"1707.03237","title":"Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentations","created":"2017-07-11","cited_by_count":620},{"id":"2304.06718","title":"Segment Everything Everywhere All at Once","created":"2023-04-13","cited_by_count":548},{"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":"2103.04918","title":"A Survey of Embodied AI: From Simulators to Research Tasks","created":"2021-03-08","cited_by_count":261},{"id":"2203.04838","title":"CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers","created":"2022-03-09","cited_by_count":231},{"id":"2304.07288","title":"Cross-Entropy Loss Functions: Theoretical Analysis and Applications","created":"2023-04-14","cited_by_count":210},{"id":"2211.10408","title":"CroCo v2: Improved Cross-view Completion Pre-training for Stereo Matching and Optical Flow","created":"2022-11-18","cited_by_count":166},{"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":"2103.13262","title":"FastMoE: A Fast Mixture-of-Expert Training System","created":"2021-03-24","cited_by_count":112},{"id":"1811.10943","title":"Deep Geometric Prior for Surface Reconstruction","created":"2018-11-27","cited_by_count":110},{"id":"2403.14598","title":"PSALM: Pixelwise SegmentAtion with Large Multi-Modal Model","created":"2024-03-21","cited_by_count":101},{"id":"2103.16284","title":"Locate then Segment: A Strong Pipeline for Referring Image Segmentation","created":"2021-03-30","cited_by_count":98},{"id":"1909.13603","title":"Multi-view PointNet for 3D Scene Understanding","created":"2019-09-30","cited_by_count":76},{"id":"2305.14344","title":"Siamese Masked Autoencoders","created":"2023-05-23","cited_by_count":76},{"id":"1906.12192","title":"GNN-FiLM: Graph Neural Networks with Feature-wise Linear Modulation","created":"2019-06-28","cited_by_count":75},{"id":"2402.17726","title":"VRP-SAM: SAM with Visual Reference Prompt","created":"2024-02-27","cited_by_count":75},{"id":"2503.00513","title":"Inst3D-LMM: Instance-Aware 3D Scene Understanding with Multi-modal Instruction Tuning","created":"2025-03-01","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":"2408.09110","title":"Locate Anything on Earth: Advancing Open-Vocabulary Object Detection for Remote Sensing Community","created":"2024-08-17","cited_by_count":50},{"id":"2308.01477","title":"HANDAL: A Dataset of Real-World Manipulable Object Categories with Pose Annotations, Affordances, and Reconstructions","created":"2023-08-02","cited_by_count":48},{"id":"2203.04279","title":"Probabilistic Warp Consistency for Weakly-Supervised Semantic Correspondences","created":"2022-03-08","cited_by_count":30},{"id":"2404.00469","title":"SceneGraphLoc: Cross-Modal Coarse Visual Localization on 3D Scene Graphs","created":"2024-03-30","cited_by_count":29},{"id":"2510.24711","title":"Routing Matters in MoE: Scaling Diffusion Transformers with Explicit Routing Guidance","created":"2025-10-28","cited_by_count":26},{"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":"2412.20665","title":"SM3Det: A Unified Model for Multi-Modal Remote Sensing Object Detection","created":"2024-12-30","cited_by_count":22},{"id":"2405.17773","title":"XTrack: Multimodal Training Boosts RGB-X Video Object Trackers","created":"2024-05-28","cited_by_count":21},{"id":"2510.06218","title":"EgoNight: Towards Egocentric Vision Understanding at Night with a Challenging Benchmark","created":"2025-10-07","cited_by_count":19},{"id":"2409.00924","title":"MedSAM-U: Uncertainty-Guided Auto Multi-Prompt Adaptation for Reliable MedSAM","created":"2024-09-02","cited_by_count":17},{"id":"2505.12266","title":"PMQ-VE: Progressive Multi-Frame Quantization for Video Enhancement","created":"2025-05-18","cited_by_count":17},{"id":"2407.01872","title":"Referring Atomic Video Action Recognition","created":"2024-07-02","cited_by_count":16},{"id":"2412.04220","title":"Customize Segment Anything Model for Multi-Modal Semantic Segmentation with Mixture of LoRA Experts","created":"2024-12-05","cited_by_count":15},{"id":"2507.05899","title":"What You Have is What You Track: Adaptive and Robust Multimodal Tracking","created":"2025-07-08","cited_by_count":15},{"id":"2310.08276","title":"Direction-Oriented Visual-semantic Embedding Model for Remote Sensing Image-text Retrieval","created":"2023-10-12","cited_by_count":14},{"id":"2508.01699","title":"TimeExpert: An Expert-Guided Video LLM for Video Temporal Grounding","created":"2025-08-03","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":"2509.23584","title":"VividFace: High-Quality and Efficient One-Step Diffusion For Video Face Enhancement","created":"2025-09-28","cited_by_count":10},{"id":"2505.15818","title":"InstructSAM: A Training-Free Framework for Instruction-Oriented Remote Sensing Object Recognition","created":"2025-05-21","cited_by_count":8},{"id":"2506.06026","title":"O-MaMa: Learning Object Mask Matching between Egocentric and Exocentric Views","created":"2025-06-06","cited_by_count":7},{"id":"2507.21816","title":"Control Copy-Paste: Controllable Diffusion-Based Augmentation Method for Remote Sensing Few-Shot Object Detection","created":"2025-07-29","cited_by_count":7},{"id":"2410.20621","title":"Egocentric and Exocentric Methods: A Short Survey","created":"2024-10-27","cited_by_count":6},{"id":"2506.05856","title":"Cross-View Multi-Modal Segmentation @ Ego-Exo4D Challenges 2025","created":"2025-06-06","cited_by_count":5},{"id":"2511.18031","title":"Diverse Instance Generation via Diffusion Models for Enhanced Few-Shot Object Detection in Remote Sensing Images","created":"2025-11-22","cited_by_count":5},{"id":"2303.00952","title":"Towards Activated Muscle Group Estimation in the Wild","created":"2023-03-02","cited_by_count":4},{"id":"2306.06472","title":"Modeling Structural Similarities between Documents for Coherence Assessment with Graph Convolutional Networks","created":"2023-06-10","cited_by_count":4},{"id":"2502.00719","title":"Vision and Language Reference Prompt into SAM for Few-shot Segmentation","created":"2025-02-02","cited_by_count":3},{"id":"2508.04050","title":"DOMR: Establishing Cross-View Segmentation via Dense Object Matching","created":"2025-08-06","cited_by_count":2},{"id":"2507.02294","title":"ViRefSAM: Visual Reference-Guided Segment Anything Model for Remote Sensing Segmentation","created":"2025-07-03","cited_by_count":1},{"id":"2509.16677","title":"Segment-to-Act: Label-Noise-Robust Action-Prompted Video Segmentation Towards Embodied Intelligence","created":"2025-09-20","cited_by_count":1},{"id":"2510.11417","title":"Robust Ego-Exo Correspondence with Long-Term Memory","created":"2025-10-13","cited_by_count":1}],"next_cursor":null}