{"total":26,"rows":[{"id":"2305.11175","title":"VisionLLM: Large Language Model is also an Open-Ended Decoder for Vision-Centric Tasks","created":"2023-05-18","cited_by_count":501,"area":null},{"id":"2403.09634","title":"OneTracker: Unifying Visual Object Tracking with Foundation Models and Efficient Tuning","created":"2024-03-14","cited_by_count":65,"area":null},{"id":"2310.16288","title":"MotionAGFormer: Enhancing 3D Human Pose Estimation with a Transformer-GCNFormer Network","created":"2023-10-25","cited_by_count":64,"area":null},{"id":"2303.11568","title":"Large AI Models in Health Informatics: Applications, Challenges, and the Future","created":"2023-03-21","cited_by_count":61,"area":null},{"id":"2309.00775","title":"Contrastive Feature Masking Open-Vocabulary Vision Transformer","created":"2023-09-02","cited_by_count":31,"area":null},{"id":"2309.01430","title":"DAT++: Spatially Dynamic Vision Transformer with Deformable Attention","created":"2023-09-04","cited_by_count":21,"area":null},{"id":"2312.07266","title":"ProxyDet: Synthesizing Proxy Novel Classes via Classwise Mixup for Open-Vocabulary Object Detection","created":"2023-12-12","cited_by_count":15,"area":null},{"id":"2404.13815","title":"Improving Group Robustness on Spurious Correlation Requires Preciser Group Inference","created":"2024-04-22","cited_by_count":15,"area":null},{"id":"2310.18737","title":"Pre-training with Random Orthogonal Projection Image Modeling","created":"2023-10-28","cited_by_count":11,"area":null},{"id":"2303.01573","title":"DejaVu: Conditional Regenerative Learning to Enhance Dense Prediction","created":"2023-03-02","cited_by_count":9,"area":null},{"id":"2404.06860","title":"Monocular 3D lane detection for Autonomous Driving: Recent Achievements, Challenges, and Outlooks","created":"2024-04-10","cited_by_count":9,"area":null},{"id":"2406.07543","title":"Vision Model Pre-training on Interleaved Image-Text Data via Latent Compression Learning","created":"2024-06-11","cited_by_count":9,"area":null},{"id":"2401.03179","title":"Multimodal Informative ViT: Information Aggregation and Distribution for Hyperspectral and LiDAR Classification","created":"2024-01-06","cited_by_count":5,"area":null},{"id":"2404.06057","title":"Unified Multi-modal Diagnostic Framework with Reconstruction Pre-training and Heterogeneity-combat Tuning","created":"2024-04-09","cited_by_count":3,"area":null},{"id":"2312.03119","title":"AI-SAM: Automatic and Interactive Segment Anything Model","created":"2023-12-05","cited_by_count":2,"area":null},{"id":"2504.13975","title":"Multiscale Tensor Summation Factorization as a New Neural Network Layer (MTS Layer) for Multidimensional Data Processing","created":"2025-04-17","cited_by_count":2,"area":null},{"id":"2306.02291","title":"3rd Place Solution for PVUW2023 VSS Track: A Large Model for Semantic Segmentation on VSPW","created":"2023-06-04","cited_by_count":1,"area":null},{"id":"2310.20424","title":"DDC-PIM: Efficient Algorithm/Architecture Co-design for Doubling Data Capacity of SRAM-based Processing-In-Memory","created":"2023-10-31","cited_by_count":1,"area":null},{"id":"2405.12861","title":"Influence of Water Droplet Contamination for Transparency Segmentation","created":"2024-05-21","cited_by_count":1,"area":null},{"id":"2406.12736","title":"Beyond Visual Appearances: Privacy-sensitive Objects Identification via Hybrid Graph Reasoning","created":"2024-06-18","cited_by_count":1,"area":null},{"id":"2406.18254","title":"Improving the Consistency in Cross-Lingual Cross-Modal Retrieval with 1-to-K Contrastive Learning","created":"2024-06-26","cited_by_count":1,"area":null},{"id":"2403.06194","title":"On depth prediction for autonomous driving using self-supervised learning","created":"2024-03-10","cited_by_count":0,"area":null},{"id":"2411.06616","title":"MEANT: Multimodal Encoder for Antecedent Information","created":"2024-11-10","cited_by_count":0,"area":null},{"id":"2411.13021","title":"Chanel-Orderer: A Channel-Ordering Predictor for Tri-Channel Natural Images","created":"2024-11-20","cited_by_count":0,"area":null},{"id":"2503.08933","title":"PromptGAR: Flexible Promptive Group Activity Recognition","created":"2025-03-11","cited_by_count":0,"area":null},{"id":"2507.20763","title":"KASportsFormer: Kinematic Anatomy Enhanced Transformer for 3D Human Pose Estimation on Short Sports Scene Video","created":"2025-07-28","cited_by_count":0,"area":null}],"next_cursor":null}