Publications

World models · Language-conditioned navigation

Human-Aware Vision-and-Language Navigation

Heng Li, Minghan Li, Zhi-Qi Cheng, Yifei Dong, Yuxuan Zhou, Jun-Yan He, Qi Dai, Teruko Mitamura, Alexander Hauptmann

Advances in Neural Information Processing Systems (NeurIPS), 2024

Datasets and Benchmarks Track · Spotlight presentation

Paper V2 Code V1 Code Website

Human-aware navigation · Vision-language benchmark

Towards Unified World Models for Visual Navigation via Memory-Augmented Planning and Foresight

Yifei Dong, Fengyi Wu, Guangyu Chen, Lingdong Kong, Xu Zhu, Qiyu Hu, Yuxuan Zhou, Jingdong Sun, Jun-Yan He, Qi Dai, Alexander G. Hauptmann, Zhi-Qi Cheng

European Conference on Computer Vision (ECCV), 2026

World models · Memory and planning

HA-VLN 2.0 human-aware navigation benchmark overview

HA-VLN 2.0: An Open Benchmark and Leaderboard for Human-Aware Navigation in Discrete and Continuous Environments with Dynamic Multi-Human Interactions

Yifei Dong, Fengyi Wu, Qi He, Heng Li, Minghan Li, Zebang Cheng, Yuxuan Zhou, Jingdong Sun, Qi Dai, Zhi-Qi Cheng, et al.

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2026

Paper Project Code

Human-aware navigation · Benchmark

GoViG goal-conditioned navigation overview

GoViG: Goal-Conditioned Visual Navigation Instruction Generation via Multimodal Reasoning

Fengyi Wu, Yifei Dong, Yilong Dai, Guangyu Chen, Qifeng Wu, Huiting Huang, Hang Wang, Qi Dai, Alexander G. Hauptmann, Zhi-Qi Cheng

Findings of the Association for Computational Linguistics: ACL 2026

Paper Project

Navigation instructions · Multimodal reasoning

Multi-View Image Generation from a Single View

Bo Zhao, Xiao Wu, Zhi-Qi Cheng, Hao Liu, Zequn Jie, Jiashi Feng

ACM International Conference on Multimedia (ACM Multimedia), 2018

Oral presentation

Novel-view synthesis · Single-view generation

Robotic manipulation survey with LLMs overview

A Survey of Robotic Manipulation: From Bottom-Up Approaches to End-to-End Paradigms with LLMs

Kai Peng, Qing Li, Zhijian He, Bowen Zhang, Xianghua Fu, Bin Li, Xiaohui Wang, Zhi-Qi Cheng, Yan Yan, Xiaojiang Peng

Neurocomputing, vol. 674, article 132921, 2026

Robotic manipulation · Vision-language-action models

Workshop papers

Perceiving physical equations by observing visual scenarios

Perceiving Physical Equation by Observing Visual Scenarios

Siyu Huang, Zhi-Qi Cheng, Xi Li, Xiao Wu, Zhongfei Zhang, Alexander Hauptmann

NeurIPS Workshop on Modeling the Physical World, 2018

Visual physical reasoning · Equation discovery

Multimodal perception & reasoning

Methods for understanding scenes, activities, and human intent through visual perception, language grounding, and generation. Earlier work in retrieval and recommendation connects observations across views and domains.

Conference & journal papers

Emotion-LLaMA: Multimodal Emotion Recognition and Reasoning with Instruction Tuning

Zebang Cheng, Zhi-Qi Cheng, Jun-Yan He, Kai Wang, Yuxiang Lin, Zheng Lian, Xiaojiang Peng, Alexander Hauptmann

Advances in Neural Information Processing Systems (NeurIPS), 2024

Paper Code Website

Emotion recognition · Instruction tuning

Combo co-speech holistic 3D human motion generation overview

Combo: Co-Speech Holistic 3D Human Motion Generation and Efficient Customizable Adaptation in Harmony

Chao Xu, Mingze Sun, Zhi-Qi Cheng, Fei Wang, Yang Liu, Baigui Sun, Ruqi Huang, Alexander Hauptmann

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2025

Early access

Paper Project

Co-speech 3D motion · Parameter-efficient adaptation

MetaDesigner pipeline, glyph, and texture designer example

MetaDesigner: Advancing Artistic Typography through AI-Driven, User-Centric, and Multilingual WordArt Synthesis

Jun-Yan He, Zhi-Qi Cheng, Chenyang Li, Jingdong Sun, Qi He, Wangmeng Xiang, Hanyuan Chen, Jin-Peng Lan, Xianhui Lin, Kang Zhu, et al.

International Conference on Learning Representations (ICLR), 2025

Paper Website

Typography generation · Multilingual design

BlockGCN: Redefine Topology Awareness for Skeleton-Based Action Recognition

Yuxuan Zhou, Xudong Yan, Zhi-Qi Cheng, Yan Yan, Qi Dai, Xian-Sheng Hua

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024

Skeleton action recognition · Graph topology

ChartReader: A Unified Framework for Chart Derendering and Comprehension without Heuristic Rules

Zhi-Qi Cheng, Qi Dai, Alexander G. Hauptmann

IEEE/CVF International Conference on Computer Vision (ICCV), 2023

Chart derendering · Visual-language comprehension

Rethinking Spatial Invariance of Convolutional Networks for Object Counting

Zhi-Qi Cheng, Qi Dai, Hong Li, Jingkuan Song, Xiao Wu, Alexander G. Hauptmann

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022

Object counting · Spatial invariance

Learning spatial awareness for crowd counting

Learning Spatial Awareness to Improve Crowd Counting

Zhi-Qi Cheng, Jun-Xiu Li, Qi Dai, Xiao Wu, Alexander G. Hauptmann

IEEE/CVF International Conference on Computer Vision (ICCV), 2019

Oral presentation

Crowd counting · Spatial awareness

Video2Shop matching clothes in videos to shopping images

Video2Shop: Exact Matching Clothes in Videos to Online Shopping Images

Zhi-Qi Cheng, Xiao Wu, Yang Liu, Xian-Sheng Hua

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017

Special oral presentation

Video-to-image retrieval · Fashion search

HDFormer: High-Order Directed Transformer for 3D Human Pose Estimation

Hanyuan Chen, Jun-Yan He, Wangmeng Xiang, Zhi-Qi Cheng, Wei Liu, Hanbing Liu, Bin Luo, Yifeng Geng, Xuansong Xie

International Joint Conference on Artificial Intelligence (IJCAI), 2023

3D human pose · Directed attention

GSRFormer: Grounded Situation Recognition Transformer with Alternate Semantic Attention Refinement

Zhi-Qi Cheng, Qi Dai, Siyao Li, Teruko Mitamura, Alexander Hauptmann

ACM International Conference on Multimedia (ACM Multimedia), 2022

Oral presentation

Grounded situation recognition · Semantic attention

Video eCommerce online video advertising overview

Video eCommerce: Towards Online Video Advertising

Zhi-Qi Cheng, Yang Liu, Xiao Wu, Xian-Sheng Hua

ACM Multimedia Conference (ACM Multimedia), 2016

Oral presentation · ACM SCF Best Student Paper Award

Video advertising · Online matching

Video eCommerce++: Toward Large-Scale Online Video Advertising

Zhi-Qi Cheng, Xiao Wu, Yang Liu, Xian-Sheng Hua

IEEE Transactions on Multimedia (TMM), 2017

Video advertising · Cross-media matching

Improving multi-column CNN for crowd counting overview

Improving the Learning of Multi-Column Convolutional Neural Network for Crowd Counting

Zhi-Qi Cheng, Jun-Xiu Li, Qi Dai, Xiao Wu, Jun-Yan He, Alexander G. Hauptmann

ACM International Conference on Multimedia (ACM Multimedia), 2019

Crowd counting · Multi-column learning

SHIELD EV battery supply-chain disruption framework

SHIELD: LLM-Driven Schema Induction for Predictive Analytics in EV Battery Supply Chain Disruptions

Zhi-Qi Cheng, Yifei Dong, Aike Shi, Wei Liu, Yuzhi Hu, Jason O’Connor, Alexander G. Hauptmann, Kate Whitefoot

Conference on Empirical Methods in Natural Language Processing: Industry Track (EMNLP), 2024

Oral presentation

Paper Code Website

Schema induction · EV supply-chain prediction

Implicit Temporal Modeling with Learnable Alignment for Video Recognition

Shuyuan Tu, Qi Dai, Zuxuan Wu, Zhi-Qi Cheng, Han Hu, Yu-Gang Jiang

IEEE/CVF International Conference on Computer Vision (ICCV), 2023

Oral presentation

Video recognition · Temporal alignment

StableAnimator: High-Quality Identity-Preserving Human Image Animation

Shuyuan Tu, Zhen Xing, Xintong Han, Zhi-Qi Cheng, Qi Dai, Chong Luo, Zuxuan Wu

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025

Paper Code Website

Human image animation · Identity preservation

MotionFollower video motion editing via score-guided diffusion

MotionFollower: Editing Video Motion via Score-Guided Diffusion

Shuyuan Tu, Qi Dai, Zihao Zhang, Sicheng Xie, Zhi-Qi Cheng, Chong Luo, Xintong Han, Zuxuan Wu, Yu-Gang Jiang

IEEE/CVF International Conference on Computer Vision (ICCV), 2025

Paper Website Code

Video motion editing · Diffusion models

MotionEditor: Editing Video Motion via Content-Aware Diffusion

Shuyuan Tu, Qi Dai, Zhi-Qi Cheng, Han Hu, Xintong Han, Zuxuan Wu, Yu-Gang Jiang

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024

Video motion editing · Content-aware diffusion

FaceChain-ImagineID listening and imagining examples

FaceChain-ImagineID: Freely Crafting High-Fidelity Diverse Talking Faces from Disentangled Audio

Chao Xu, Yang Liu, Jiazheng Xing, Weida Wang, Mingze Sun, Jun Dan, Tianxin Huang, Siyuan Li, Zhi-Qi Cheng, Ying Tai, et al.

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024

Talking-face generation · Audio conditioning

VDAct: A Video-grounded Dialogue Dataset and Metric for Event-driven Activities

Wiradee Imrattanatrai, Masaki Asada, Kimihiro Hasegawa, Zhi-Qi Cheng, Ken Fukuda, Teruko Mitamura

AAAI Conference on Artificial Intelligence (AAAI), 2025

Oral presentation

Paper Code & Data

Video-grounded dialogue · Activity understanding

ProMQA procedural activity understanding

ProMQA: Question Answering Dataset for Multimodal Procedural Activity Understanding

Kimihiro Hasegawa, Wiradee Imrattanatrai, Zhi-Qi Cheng, Masaki Asada, Susan Holm, Yuran Wang, Ken Fukuda, Teruko Mitamura

Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL), 2025

Oral presentation

Paper Code & Data

Procedural understanding · Multimodal question answering

POPoS parallel optimal position search overview

POPoS: Improving Efficient and Robust Facial Landmark Detection with Parallel Optimal Position Search

Chong-Yang Xiang, Jun-Yan He, Zhi-Qi Cheng, Xiao Wu, Xian-Sheng Hua

AAAI Conference on Artificial Intelligence (AAAI), 2025

Facial landmarks · Position estimation

DCPT: Darkness Clue-Prompted Tracking in Night-Time UAVs

Jiawen Zhu, Huayi Tang, Zhi-Qi Cheng, Jun-Yan He, Bin Luo, Shihao Qiu, Shengming Li, Huchuan Lu

IEEE International Conference on Robotics and Automation (ICRA), 2024

Night-time UAV tracking · Visual prompts

KeyPosS: Plug-and-Play Facial Landmark Detection through GPS-Inspired True-Range Multilateration

Xu Bao, Zhi-Qi Cheng, Jun-Yan He, Wangmeng Xiang, Chenyang Li, Jingdong Sun, Hanbing Liu, Wei Liu, Bin Luo, Yifeng Geng, et al.

ACM International Conference on Multimedia (ACM Multimedia), 2023

Facial landmarks · Multilateration

PoSynDA: Multi-Hypothesis Pose Synthesis Domain Adaptation for Robust 3D Human Pose Estimation

Hanbing Liu, Jun-Yan He, Zhi-Qi Cheng, Wangmeng Xiang, Qize Yang, Wenhao Chai, Gaoang Wang, Xu Bao, Bin Luo, Yifeng Geng, et al.

ACM International Conference on Multimedia (ACM Multimedia), 2023

3D human pose · Domain adaptation

Disentangled product-of-experts for online multi-view anomaly detection

Debunking Free Fusion Myth: Online Multi-View Anomaly Detection with Disentangled Product-of-Experts Modeling

Hao Wang, Zhi-Qi Cheng, Jingdong Sun, Xin Yang, Xiao Wu, Hongyang Chen, Yan Yang

ACM International Conference on Multimedia (ACM Multimedia), 2023

Multi-view anomaly detection · Disentangled modeling

Multi-granularity cross-domain alignment for anomaly segmentation

Improving Anomaly Segmentation with Multi-Granularity Cross-Domain Alignment

Ji Zhang, Xiao Wu, Zhi-Qi Cheng, Qi He, Wei Li

ACM International Conference on Multimedia (ACM Multimedia), 2023

Anomaly segmentation · Cross-domain alignment

Parallel multi-view feature augmentation for real-time semantic segmentation

Real-Time Semantic Segmentation with Parallel Multiple Views Feature Augmentation

Jian-Jun Qiao, Zhi-Qi Cheng, Xiao Wu, Wei Li, Ji Zhang

ACM International Conference on Multimedia (ACM Multimedia), 2022

Semantic segmentation · Multi-view features

CrossNet crowd counting with localization overview

CrossNet: Boosting Crowd Counting with Localization

Ji Zhang, Zhi-Qi Cheng, Xiao Wu, Wei Li, Jian-Jun Qiao

ACM International Conference on Multimedia (ACM Multimedia), 2022

Crowd counting · Localization

Appearance-aware pose stylizer person image generation

Generating Person Images with Appearance-Aware Pose Stylizer

Siyu Huang, Haoyi Xiong, Zhi-Qi Cheng, Qingzhong Wang, Xingran Zhou, Bihan Wen, Jun Huan, Dejing Dou

International Joint Conference on Artificial Intelligence (IJCAI), 2020

Person-image generation · Appearance and pose

Large Language Model Agents in Finance: A Survey Bridging Research, Practice, and Real-World Deployment

Yifei Dong, Fengyi Wu, Kunlin Zhang, Yilong Dai, Sanjian Zhang, Wanghao Ye, Sihan Chen, Zhi-Qi Cheng

Findings of the Association for Computational Linguistics: EMNLP 2025

Paper Website

LLM agents · Finance

IVAC-P2L video action counting with irregular repetition priors

IVAC-P2L: Leveraging Irregular Repetition Priors for Improving Video Action Counting

Hang Wang, Zhi-Qi Cheng, Youtian Du, Lei Zhang

IEEE Transactions on Multimedia (TMM), 2025

Video action counting · Repetition modeling

On the Selection of Anchors and Targets for Video Hyperlinking

Zhi-Qi Cheng, Hao Zhang, Xiao Wu, Chong-Wah Ngo

ACM International Conference on Multimedia Retrieval (ICMR), 2017

Special oral presentation

Video hyperlinking · Anchor and target selection

UMETTS emotional text-to-speech synthesis overview

UMETTS: A Unified Framework for Emotional Text-to-Speech Synthesis with Multimodal Prompts

Zhi-Qi Cheng, Xiang Li, Jun-Yan He, Junyao Chen, Xiaomao Fan, Xiaojiang Peng, Alexander G. Hauptmann

IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2025

Emotional speech synthesis · Multimodal prompts

SituLM: Leveraging Visual Instruction Tuning and an Augmented SWiG Dataset for Enhanced Grounded Situation Recognition

Yuran Wang, Zhi-Qi Cheng

IEEE International Conference on Multimedia and Expo (ICME), 2025

Oral presentation

Grounded situation recognition · Visual instruction tuning

ProContEXT progressive context transformer for tracking

ProContEXT: Exploring Progressive Context Transformer for Tracking

Jin-Peng Lan, Zhi-Qi Cheng, Jun-Yan He, Chenyang Li, Bin Luo, Xu Bao, Wangmeng Xiang, Yifeng Geng, Xuansong Xie

IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2023

Oral presentation

Object tracking · Context modeling

DeformAvatar: Point-Based Human Avatar Re-targeting and Rendering

Renyi Zhan, Zhi-Qi Cheng, Junyao Chen, Xiaojiang Peng

IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2025

Human avatars · 3D retargeting and rendering

RTPCA refined temporal pyramidal compression-and-amplification transformer overview

Refined Temporal Pyramidal Compression-and-Amplification Transformer for 3D Human Pose Estimation

Hanbing Liu, Zhi-Qi Cheng, Wangmeng Xiang, Jun-Yan He, Bin Luo, Yifeng Geng, Xuansong Xie

IEEE International Conference on Multimedia and Expo (ICME), 2025

3D pose estimation · Temporal modeling

Music2P: A Multi-Modal AI-Driven Tool for Simplifying Album Cover Design

Joong Ho Choi, Geonyeong Choi, Ji Eun Han, Wonjin Yang, Zhi-Qi Cheng

ACM International Conference on Information and Knowledge Management (CIKM), 2024

Demo Track

Album-cover generation · Multimodal design

Stacked Pooling for scale-invariant crowd counting overview

Stacked Pooling for Boosting Scale Invariance of Crowd Counting

Siyu Huang, Xi Li, Zhi-Qi Cheng, Zhongfei Zhang, Alexander Hauptmann

IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2020

Crowd counting · Scale invariance

LEAF semi-supervised facial expression recognition overview

LEAF: Unveiling Two Sides of the Same Coin in Semi-Supervised Facial Expression Recognition

Fan Zhang, Zhi-Qi Cheng, Jian Zhao, Xiaojiang Peng, Xuelong Li

Computer Vision and Image Understanding (CVIU), 2025

Facial expression recognition · Semi-supervised learning

WordArt Designer: User-Driven Artistic Typography Synthesis Using Large Language Models

Jun-Yan He, Zhi-Qi Cheng, Chenyang Li, Jingdong Sun, Wangmeng Xiang, Xianhui Lin, Xiaoyang Kang, Zengke Jin, Yusen Hu, Bin Luo, et al.

Conference on Empirical Methods in Natural Language Processing: Industry Track (EMNLP), 2023

Paper Project Model Studio Demo

Artistic typography · Language-guided generation

DB-LSTM densely-connected bi-directional LSTM for action recognition

DB-LSTM: Densely-Connected Bi-Directional LSTM for Human Action Recognition

Jun-Yan He, Xiao Wu, Zhi-Qi Cheng, Zhaoquan Yuan, Yu-Gang Jiang

Neurocomputing, 2021

Human action recognition · Temporal modeling

Personalized Clothing Recommendation Combining User Social Circle and Fashion Style Consistency

Guang-Lu Sun, Zhi-Qi Cheng, Xiao Wu, Qiang Peng

Multimedia Tools and Applications, 2018

Clothing recommendation · Social and style signals

Workshop papers

Securing the Skies: A Comprehensive Survey on Anti-UAV Methods, Benchmarking, and Future Directions

Yifei Dong, Fengyi Wu, Sanjian Zhang, Guangyu Chen, Yuzhi Hu, Masumi Yano, Jingdong Sun, Siyu Huang, Feng Liu, Qi Dai, Zhi-Qi Cheng, et al.

IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW): Anti-UAV Workshop, 2025

Best Paper Award

Anti-UAV methods · Survey and benchmarking

Why We Feel emotional reasoning with multimodal large language models

Why We Feel: Breaking Boundaries in Emotional Reasoning with Multimodal Large Language Models

Yuxiang Lin, Jingdong Sun, Zhi-Qi Cheng, Jue Wang, Haomin Liang, Zebang Cheng, Yifei Dong, Jun-Yan He, Xiaojiang Peng, Xian-Sheng Hua

IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW): NEXD Workshop, 2025

Oral presentation

Emotion reasoning · Multimodal language models

WordArt Designer API: User-Driven Artistic Typography Synthesis with LLMs on ModelScope

Jun-Yan He, Zhi-Qi Cheng, Chenyang Li, Jingdong Sun, Wangmeng Xiang, Xianhui Lin, Xiaoyang Kang, Zengke Jin, Yusen Hu, Bin Luo, et al.

NeurIPS Workshop on Machine Learning for Creativity and Design, 2023

Spotlight presentation

Paper Project Model Studio Demo

Artistic typography · Interactive generation

MIPS at SemEval-2024 Task 3: Multimodal Emotion-Cause Pair Extraction in Conversations with Multimodal Language Models

Zebang Cheng, Fuqiang Niu, Yuxiang Lin, Zhi-Qi Cheng, Bowen Zhang, Xiaojiang Peng

18th International Workshop on Semantic Evaluation (SemEval), 2024

3rd place

Emotion-cause extraction · Multimodal conversations

SZTU-CMU at MER2024: Improving Emotion-LLaMA with Conv-Attention for Multimodal Emotion Recognition

Zebang Cheng, Shuyuan Tu, Dawei Huang, Minghan Li, Xiaojiang Peng, Zhi-Qi Cheng, Alexander G. Hauptmann

2nd International Workshop on Multimodal and Responsible Affective Computing (MRAC), 2024

First place, MER2024 MER-NOISE track

Multimodal emotion recognition · Challenge system

Preprints

Emotion-LLaMAv2 and MMEVerse benchmark overview

Emotion-LLaMAv2 and MMEVerse: A New Framework and Benchmark for Multimodal Emotion Understanding

Xiaojiang Peng, Jingyi Chen, Zebang Cheng, Bao Peng, Fengyi Wu, Yifei Dong, Shuyuan Tu, Qiyu Hu, Huiting Huang, Yuxiang Lin, et al.

arXiv preprint, 2026

Paper Code & Benchmark

Emotion understanding · Multimodal benchmark

ATSS anomalous temporal self-similarity for AI-generated video detection

ATSS: Detecting AI-Generated Videos via Anomalous Temporal Self-Similarity

Hang Wang, Chao Shen, Lei Zhang, Zhi-Qi Cheng

arXiv preprint, 2026

Generated-video detection · Digital forensics

Cell Behavior Video Classification Challenge overview

Cell Behavior Video Classification Challenge, a benchmark for computer vision methods in time-lapse microscopy

Diego Ulisse Pizzagalli, Raffaella Fiamma Cabini, Deborah Barkauskas, Guangyu Chen, Zhi-Qi Cheng, et al.

arXiv preprint, 2026

Paper Website Code

Cell behavior · Video classification

StableAnimator++ pose misalignment and face distortion mitigation

StableAnimator++: Overcoming Pose Misalignment and Face Distortion for Human Image Animation

Shuyuan Tu, Zhen Xing, Xintong Han, Zhi-Qi Cheng, Qi Dai, Chong Luo, Zuxuan Wu, Yu-Gang Jiang

arXiv preprint, 2025

Paper Website Code

Human image animation · Pose alignment

Tracking with Human-Intent Reasoning

Jiawen Zhu, Zhi-Qi Cheng, Jun-Yan He, Chenyang Li, Bin Luo, Huchuan Lu, Yifeng Geng, Xuansong Xie

arXiv preprint, 2023

Visual tracking · Human-intent reasoning

Hypergraph Transformer for Skeleton-Based Action Recognition

Yuxuan Zhou, Zhi-Qi Cheng, Chao Li, Yanwen Fang, Yifeng Geng, Xuansong Xie, Margret Keuper

arXiv preprint, 2022

Skeleton action recognition · Hypergraphs

Reports & other research outputs

CMU CHRONOS-KAIROS Final Systems Description

Teruko Mitamura, David R. Mortensen, Alex Hauptmann, Yiming Yang, Graham Neubig, Anatole Gersham, Alan W. Black, Zhi-Qi Cheng, Susan Holm, Yukari Yamakawa

DARPA KAIROS final systems report, 2024

Multimodal event understanding · System integration

Determining Recommended Object

Zhiqi Cheng, Yang Liu, Xiansheng Hua

U.S. Patent 10,671,851, 2020

Patent

Recommendation · Granted patent

VIREO@TRECVID 2017 video-to-text and ad-hoc video search overview

VIREO@TRECVID 2017: Video-to-Text, Ad-hoc Video Search and Video Hyperlinking

Phuong Anh Nguyen, Qing Li, Zhi-Qi Cheng, Yi-Jie Lu, Hao Zhang, Xiao Wu, Chong-Wah Ngo

TREC Video Retrieval Evaluation (TRECVID), 2017

Video-text retrieval · TRECVID evaluation

Minimizing Risk in Video Hyperlinking

Chong-Wah Ngo, Zhi-Qi Cheng, Xiao Wu

TREC Video Retrieval Evaluation (TRECVID), 2017

Keynote presentation

Slides

Video hyperlinking · Risk minimization

Reliable & efficient AI

Methods for adaptation, calibration, transferable representations, and efficient inference, supporting reliable predictions across changing data and environments.

Conference & journal papers

Lossless Hierarchical Speculative Decoding overview

Overcoming Joint Intractability with Lossless Hierarchical Speculative Decoding

Yuxuan Zhou, Fei Huang, Heng Li, Fengyi Wu, Tianyu Wang, Jianwei Zhang, Junyang Lin, Zhi-Qi Cheng

International Conference on Learning Representations (ICLR), 2026

Oral presentation

Lossless inference · Speculative decoding

MaxSup Grad-CAM visualization comparison

MaxSup: Overcoming Representation Collapse in Label Smoothing

Yuxuan Zhou, Heng Li, Zhi-Qi Cheng, Xudong Yan, Mario Fritz, Margret Keuper

Advances in Neural Information Processing Systems (NeurIPS), 2025

Oral presentation

Label smoothing · Representation learning

Towards Calibrated Robust Fine-Tuning of Vision-Language Models

Changdae Oh, Hyesu Lim, Mijoo Kim, Dongyoon Han, Sangdoo Yun, Jaegul Choo, Alexander Hauptmann, Zhi-Qi Cheng, Kyungwoo Song

Advances in Neural Information Processing Systems (NeurIPS), 2024

Vision-language adaptation · Calibration

Learning to Transfer generalizable attribute learning overview

Learning to Transfer: Generalizable Attribute Learning with Multitask Neural Model Search

Zhi-Qi Cheng, Xiao Wu, Siyu Huang, Jun-Xiu Li, Alexander G. Hauptmann, Qiang Peng

ACM International Conference on Multimedia (ACM Multimedia), 2018

Spotlight presentation

Attribute learning · Transfer and model search

BlackVIP black-box visual prompting for foundation model adaptation

Robust Adaptation of Foundation Models with Black-Box Visual Prompting

Changdae Oh, Gyeongdeok Seo, Geunyoung Jung, Zhi-Qi Cheng, Hosik Choi, Jiyoung Jung, Kyungwoo Song

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2026

Visual prompting · Black-box adaptation

Emphasizing Discriminative Features for Dataset Distillation in Complex Scenarios

Kai Wang, Zekai Li, Zhi-Qi Cheng, Samir Khaki, Ahmad Sajedi, Ramakrishna Vedantam, Konstantinos N. Plataniotis, Alexander Hauptmann, Yang You

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025

Dataset distillation · Discriminative representations

PROS: Prompting-to-Simulate Generalized Knowledge for Universal Cross-Domain Retrieval

Kaipeng Fang, Jingkuan Song, Lianli Gao, Pengpeng Zeng, Zhi-Qi Cheng, Xiyao Li, Heng-Tao Shen

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024

Cross-domain retrieval · Prompt adaptation

GNAS greedy neural architecture search overview

GNAS: A Greedy Neural Architecture Search Method for Multi-Attribute Learning

Siyu Huang, Xi Li, Zhi-Qi Cheng, Zhongfei Zhang, Alexander Hauptmann

ACM International Conference on Multimedia (ACM Multimedia), 2018

Oral presentation

Neural architecture search · Multi-attribute learning

UCDR-Adapter: Exploring Adaptation of Pre-Trained Vision-Language Models for Universal Cross-Domain Retrieval

Haoyu Jiang, Zhi-Qi Cheng, Gabriel Moreira, Jiawen Zhu, Jingdong Sun, Bukun Ren, Jun-Yan He, Qi Dai, Xian-Sheng Hua

IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2025

Cross-domain retrieval · Model adaptation

Preprints

Never Compromise to Vulnerabilities: A Comprehensive Survey on AI Governance

Yuchu Jiang, Jian Zhao, Yuchen Yuan, Tianle Zhang, Yao Huang, Yanghao Zhang, Yan Wang, Yanshu Li, Xizhong Guo, Yusheng Zhao, et al.

arXiv preprint, 2025

Paper Project

AI governance · Survey

Prioritize Alignment in Dataset Distillation

Zekai Li, Ziyao Guo, Wangbo Zhao, Tianle Zhang, Zhi-Qi Cheng, Samir Khaki, Kaipeng Zhang, Ahmad Sajedi, Konstantinos N. Plataniotis, Kai Wang, et al.

arXiv preprint, 2024