activity
20222025
most citedDeep Laparoscopic Stereo Matching with Transformers

1 citations · 2 across the 4 of their papers we have counts for

collaborators

9 papers

cs.CV2024

Exploring Self- and Cross-Triplet Correlations for Human-Object Interaction Detection

Weibo Jiang, Weihong Ren, Jiandong Tian +3

Human-Object Interaction (HOI) detection plays a vital role in scene understanding, which aims to predict the HOI triplet in the form of <human, object, action>. Existing methods m…

cs.LG20231 cited

XAI for In-hospital Mortality Prediction via Multimodal ICU Data

Xingqiao Li, Jindong Gu, Zhiyong Wang +3

Predicting in-hospital mortality for intensive care unit (ICU) patients is key to final clinical outcomes. AI has shown advantaged accuracy but suffers from the lack of explainabil…

cs.LG20232 cited

Online Clustering of Bandits with Misspecified User Models

Zhiyong Wang, Jize Xie, Xutong Liu +2

The contextual linear bandit is an important online learning problem where given arm features, a learning agent selects an arm at each round to maximize the cumulative rewards in t…

cs.CL2023

Efficient and Interpretable Compressive Text Summarisation with Unsupervised Dual-Agent Reinforcement Learning

Peggy Tang, Junbin Gao, Lei Zhang +1

Recently, compressive text summarisation offers a balance between the conciseness issue of extractive summarisation and the factual hallucination issue of abstractive summarisation…

cs.CV2023

Full Resolution Repetition Counting

Jianing Li, Bowen Chen, Zhiyong Wang +1

Given an untrimmed video, repetitive actions counting aims to estimate the number of repetitions of class-agnostic actions. To handle the various length of videos and repetitive ac…

cs.CV20231 cited

Continuous Intermediate Token Learning with Implicit Motion Manifold for Keyframe Based Motion Interpolation

Clinton Ansun Mo, Kun Hu, Chengjiang Long +1

Deriving sophisticated 3D motions from sparse keyframes is a particularly challenging problem, due to continuity and exceptionally skeletal precision. The action features are often…