MX
Mingze Xu
cs.CVcs.AIcs.LGcs.CLcs.ROcs.MM
On Valency
published · living versionsW_hcxxvb56·v1 · currentpublished
EditAgent: Rethinking Agentic Image Editing
with Haiyang Xu, Tianyu Wang, Jialu Li, Jiteng Mu +3
1 version
Preprints & journals
29 papers in the corpus · 2017–2025AToken: A Unified Tokenizer for Vision2509.14476v2 · Jiasen Lu, Liangchen Song, Mingze Xu et al.2025 · 0 citationsarXiv
Apple Intelligence Foundation Language Models: Tech Report 20252507.13575v3 · Ethan Li, Anders Boesen Lindbo Larsen, Chen Zhang et al.2025 · 0 citationsarXiv
UniGen: Enhanced Training & Test-Time Strategies for Unified Multimodal Understanding and Generation2505.14682v1 · Rui Tian, Mingfei Gao, Mingze Xu et al.2025 · 2 citationsarXiv
StreamBridge: Turning Your Offline Video Large Language Model into a Proactive Streaming Assistant2505.05467v2 · Haibo Wang, Bo Feng, Zhengfeng Lai et al.2025 · 8 citationsarXiv
SlowFast-LLaVA-1.5: A Family of Token-Efficient Video Large Language Models for Long-Form Video Understanding2503.18943v2 · Mingze Xu, Mingfei Gao, Shiyu Li et al.2025 · 0 citationsarXiv
MM1.5: Methods, Analysis & Insights from Multimodal LLM Fine-tuning2409.20566v1 · Haotian Zhang, Mingfei Gao, Zhe Gan et al.2024 · 1 citationarXiv
SlowFast-LLaVA: A Strong Training-Free Baseline for Video Large Language Models2407.15841v2 · Mingze Xu, Mingfei Gao, Zhe Gan et al.2024 · 5 citationsarXiv
SkeleTR: Towrads Skeleton-based Action Recognition in the Wild2309.11445v1 · Haodong Duan, Mingze Xu, Bing Shuai et al.2023 · 0 citationsarXiv
DoTA: Unsupervised Detection of Traffic Anomaly in Driving Videos.35157576 · Yao, Yu, Wang, Xizi, Xu, Mingze et al.2023 · 125 citationsIEEE transactions on pattern analysis and machine intelligence. 2023;45(1):444-459
An In-depth Study of Stochastic Backpropagation2210.00129v1 · Jun Fang, Mingze Xu, Hao Chen et al.2022 · 1 citationarXiv
Stochastic Backpropagation: A Memory Efficient Strategy for Training Video Models2203.16755v1 · Feng Cheng, Mingze Xu, Yuanjun Xiong et al.2022 · 11 citationsarXiv
MeMOT: Multi-Object Tracking with Memory2203.16761v1 · Jiarui Cai, Mingze Xu, Wei Li et al.2022 · 258 citationsarXiv
Long Short-Term Transformer for Online Action Detection2107.03377v3 · Mingze Xu, Yuanjun Xiong, Hao Chen et al.2021 · 98 citationsarXiv
Semi-TCL: Semi-Supervised Track Contrastive Representation Learning2107.02396v1 · Wei Li, Yuanjun Xiong, Shuo Yang et al.2021 · 35 citationsarXiv
TubeR: Tubelet Transformer for Video Action Detection2104.00969v5 · Jiaojiao Zhao, Yanyi Zhang, Xinyu Li et al.2021 · 101 citationsarXiv
Stepwise Goal-Driven Networks for Trajectory Prediction2103.14107v3 · Chuhua Wang, Yuchen Wang, Mingze Xu et al.2021 · 211 citationsin IEEE Robotics and Automation Letters, vol. 7, no. 2, pp. 2716-2723, April 2022
Learning Self-Consistency for Deepfake Detection2012.09311v2 · Tianchen Zhao, Xiang Xu, Mingze Xu et al.2020 · 383 citationsarXiv
Deep Tiered Image Segmentation For Detecting Internal Ice Layers in Radar Imagery2010.03712v3 · Yuchen Wang, Mingze Xu, John Paden et al.2020 · 15 citationsarXiv
When, Where, and What? A New Dataset for Anomaly Detection in Driving Videos2004.03044v1 · Yu Yao, Xizi Wang, Mingze Xu et al.2020 · 38 citationsarXiv
Embodied Visual Recognition1904.04404v1 · Jianwei Yang, Zhile Ren, Mingze Xu et al.2019 · 20 citationsarXiv
StartNet: Online Detection of Action Start in Untrimmed Videos1903.09868v1 · Mingfei Gao, Mingze Xu, Larry S. Davis et al.2019 · 62 citationsarXiv
Unsupervised Traffic Accident Detection in First-Person Videos1903.00618v4 · Yu Yao, Mingze Xu, Yuchen Wang et al.2019 · 230 citationsarXiv
Temporal Recurrent Networks for Online Action Detection1811.07391v2 · Mingze Xu, Mingfei Gao, Yi-Ting Chen et al.2018 · 202 citationsarXiv
Egocentric Vision-based Future Vehicle Localization for Intelligent Driving Assistance Systems1809.07408v2 · Yu Yao, Mingze Xu, Chiho Choi et al.2018 · 152 citationsarXiv
Joint Person Segmentation and Identification in Synchronized First- and Third-person Videos1803.11217v2 · Mingze Xu, Chenyou Fan, Yuchen Wang et al.2018 · 36 citationsarXiv
Fully-Coupled Two-Stream Spatiotemporal Networks for Extremely Low Resolution Action Recognition1801.03983v1 · Mingze Xu, Aidean Sharghi, Xin Chen et al.2018 · 35 citationsarXiv
Multi-Task Spatiotemporal Neural Networks for Structured Surface Reconstruction1801.03986v2 · Mingze Xu, Chenyou Fan, John D Paden et al.2018 · 15 citationsarXiv
Automatic Estimation of Ice Bottom Surfaces from Radar Imagery1712.07758v1 · Mingze Xu, David J Crandall, Geoffrey C Fox et al.2017 · 27 citationsarXiv
Identifying First-person Camera Wearers in Third-person Videos1704.06340v1 · Chenyou Fan, Jangwon Lee, Mingze Xu et al.2017 · 60 citationsarXiv
Career total: 41 works. 29 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.