{"total":15,"rows":[{"id":"2503.19108","title":"Your ViT is Secretly an Image Segmentation Model","created":"2025-03-24","cited_by_count":63,"area":null},{"id":"2510.27432","title":"Mitigating Semantic Collapse in Partially Relevant Video Retrieval","created":"2025-10-31","cited_by_count":5,"area":null},{"id":"2511.05449","title":"How Many Tokens Do 3D Point Cloud Transformer Architectures Really Need?","created":"2025-11-07","cited_by_count":4,"area":null},{"id":"2603.25398","title":"PMT: Plain Mask Transformer for Image and Video Segmentation with Frozen Vision Encoders","created":"2026-03-26","cited_by_count":3,"area":null},{"id":"2602.08224","title":"Efficient-SAM2: Accelerating SAM2 with Object-Aware Visual Encoding and Memory Retrieval","created":"2026-02-09","cited_by_count":2,"area":null},{"id":"2502.16654","title":"VPNeXt -- Rethinking Dense Decoding for Plain Vision Transformer","created":"2025-02-23","cited_by_count":1,"area":null},{"id":"2509.10334","title":"I-Segmenter: Integer-Only Vision Transformer for Efficient Semantic Segmentation","created":"2025-09-12","cited_by_count":1,"area":null},{"id":"2508.04058","title":"TCSAFormer: Efficient Vision Transformer with Token Compression and Sparse Attention for Medical Image Segmentation","created":"2025-08-06","cited_by_count":0,"area":null},{"id":"2508.05851","title":"Temporal Cluster Assignment for Efficient Real-Time Video Segmentation","created":"2025-08-07","cited_by_count":0,"area":null},{"id":"2509.23672","title":"Token Merging via Spatiotemporal Information Mining for Surgical Video Understanding","created":"2025-09-28","cited_by_count":0,"area":null},{"id":"2604.00634","title":"LiPS: Lightweight Panoptic Segmentation for Resource-Constrained Robotics","created":"2026-04-01","cited_by_count":0,"area":null},{"id":"2604.16854","title":"Certainty Is Redundant: Token Sparsification for Efficient Camouflaged Object Detection with Vision Foundation Models","created":"2026-04-18","cited_by_count":0,"area":null},{"id":"2607.17656","title":"BMFA: Boundary-Minority Free-Energy Adaptive Screening","created":"2026-07-20","cited_by_count":0,"area":null},{"id":"2607.19811","title":"Lean-SAM2: Target-Anchored Memory and Encoder Acceleration for SAM2","created":"2026-07-22","cited_by_count":0,"area":null},{"id":"2608.23142","title":"How Merge-Tolerant Are Vision Transformers for Wheat Phenotyping?","created":"2026-08-24","cited_by_count":0,"area":null}],"next_cursor":null}