papers

Publications (13)

cs.CV2019

Adaptive Unimodal Cost Volume Filtering for Deep Stereo Matching

Youmin Zhang, Yimin Chen, Xiao Bai +4

State-of-the-art deep learning based stereo matching approaches treat disparity estimation as a regression problem, where loss function is directly defined on true disparities and…

cs.AI2026

UESF-Bench: Benchmarking and Probing for Unified Embodied Seeking and Following

Kun Yu, Jianhua Yang, Yixiang Chen +7

The paper introduces UESF-Bench, a large-scale benchmark for unified embodied seeking and following of humans, and presents SeekFollow-VLA, a vision‑language‑action framework that…

#embodied ai#human following#language-guided navigation#benchmark
eess.SP2022

Multi-View Fusion Transformer for Sensor-Based Human Activity Recognition

Yimu Wang, Kun Yu, Yan Wang +1

As a fundamental problem in ubiquitous computing and machine learning, sensor-based human activity recognition (HAR) has drawn extensive attention and made great progress in recent…

cs.CV2024

Solution for Point Tracking Task of ECCV 2nd Perception Test Challenge 2024

Yuxuan Zhang, Pengsong Niu, Kun Yu +2

This report introduces an improved method for the Tracking Any Point~(TAP), focusing on monitoring physical surfaces in video footage. Despite their success with short-sequence sce…

cs.DB2025

Approximate Nearest Neighbor Search of Large Scale Vectors on Distributed Storage

Kun Yu, Jiabao Jin, Xiaoyao Zhong +6

Approximate Nearest Neighbor Search (ANNS) in high-dimensional space is an essential operator in many online services, such as information retrieval and recommendation. Indices con…

cs.CV2020

Feature-metric Loss for Self-supervised Learning of Depth and Egomotion

Chang Shu, Kun Yu, Zhixiang Duan +1

Photometric loss is widely used for self-supervised depth and egomotion estimation. However, the loss landscapes induced by photometric differences are often problematic for optimi…