This paper proposes MotionSpec, a motion supervision framework centered on Spectral Trajectory Consistency (STC), which constrains both motion strength across temporal frequencies and the temporal organization of motion, and introduces Local Flow Consistency (LFC), which aligns consecutive-frame optical flow between pr...
Experiments show that EDC outperforms state-of-the-art deformable convolution variants, including Deformable ConvNets V1-V4 and Entire Deformable ConvNets, across mainstream segmentation datasets with various decoder settings, and ablation studies confirm the effectiveness of each component.
Yi-Xiao Li, Xiao-Yuan Yang, Jin Jiang et al.· 0 citations
CRISP is proposed, a pre-LLM yet text-driven visual token pruning framework that preserves both instruction-relevant evidence and essential scene context that serves as a practical solution for efficient LVLM inference, especially in resource-constrained scenarios.
Xu Li, Yi Zheng, Mengyang Zhao et al.· arXiv.org· 1 citation
This work proposes a novel framework, SARTM, which customizes the powerful SAM for RGB-T semantic segmentation, and introduces a Cross-Modal Knowledge Distillation (CMKD) module that effectively achieves modality adaptation while maintaining its generalization capabilities.
This work proposes RAGMesh, a retrieval-augmented framework that leverages text-correlated geometric priors to improve high-fidelity facial synthesis and editing, and introduces Adaptive RAG-guided Supervision (AdaRAGS), a region-aware constraint that explicitly aligns textual semantics with corresponding facial region...
The Cross-Modal Dual-Path Generator (CM-DPG), a model for robust open-vocabulary SGG that enhances object-level semantic representations through joint visual-textual encoding and improves relational reasoning using complementary visual and geometric cues, is proposed.
Ming-Hao Zou, Qingtian Zeng, Shangkun Liu et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
