liaomx

DEVIL. Evaluation of Text-to-Video Generation Models: A Dynamics Perspective[NeurIPS 2024].

AttentionShift. Official Implementation of AttentionShift: Iteratively Estimated Part-based Attention Map for Pointly Supervised Instance Segmentation

SPE. Official implementation of ECCV2022 paper End-to-End Weakly Supervised Object Detection with Sparse Proposal Evolution

Teacache-xDiT. Combining Teacache with xDiT to Accelerate Visual Generation Models

OW-IAA. Open World Image Aesthetic Assessment (CVPR 2026 Findings)