{"total":16,"rows":[{"id":"2506.05312","title":"Do It Yourself: Learning Semantic Correspondence from Pseudo-Labels","created":"2025-06-05","cited_by_count":13,"area":null},{"id":"2507.17657","title":"Attention (as Discrete-Time Markov) Chains","created":"2025-07-23","cited_by_count":11,"area":null},{"id":"2508.00746","title":"GECO: Geometrically Consistent Embedding with Lightspeed Inference","created":"2025-08-01","cited_by_count":6,"area":null},{"id":"2505.21062","title":"Inverse Virtual Try-On: Generating Multi-Category Product-Style Images from Clothed Individuals","created":"2025-05-27","cited_by_count":4,"area":null},{"id":"2505.18060","title":"Semantic Correspondence: Unified Benchmarking and a Strong Baseline","created":"2025-05-23","cited_by_count":3,"area":null},{"id":"2509.21263","title":"Towards Geometry-Grounded Dense Semantic Matching with VGGT Priors","created":"2025-09-25","cited_by_count":3,"area":null},{"id":"2603.23906","title":"GenMask: Adapting DiT for Segmentation via Direct Mask Generation","created":"2026-03-25","cited_by_count":3,"area":null},{"id":"2509.08908","title":"Diffusion-Based Action Recognition Generalizes to Untrained Domains","created":"2025-09-10","cited_by_count":2,"area":null},{"id":"2606.07034","title":"ForensicConcept: Transferable Forensic Concepts for AIGI Detection","created":"2026-06-05","cited_by_count":2,"area":null},{"id":"2511.18775","title":"Rethinking Garment Conditioning in Diffusion-based Virtual Try-On: Decouple, Don't Denoise","created":"2025-11-24","cited_by_count":0,"area":null},{"id":"2512.08325","title":"GeoDiffMM: Geometry-Guided Conditional Diffusion for Motion Magnification","created":"2025-12-09","cited_by_count":0,"area":null},{"id":"2605.31597","title":"SOCO: Benchmarking Semantic Object Correspondence in Vision Foundation Models","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2608.04995","title":"Promptable Animal Pose Tracking Across Species","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2609.15098","title":"LG-VLN: A Zero-Shot Vision-and-Language Navigation Framework with LangGraph State Orchestration","created":"2026-09-14","cited_by_count":0,"area":null},{"id":"2609.33217","title":"RepFlow: Reciprocal Supervision Improves Generation and Representation in Flow Models","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2610.20124","title":"DreamHMR: From Video Generation to Human Motion Modeling via Structural Focusing","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}