UMD Researchers to Have a Strong Showing at the 2022 European Conference on Computer Vision

University of Maryland researchers will present 14 papers at the European Conference on Computer Vision (ECCV 2022), to be held from October 23 to October 27, 2022. ECCV is one of the top-tier and most prestigious conferences for computer vision researchers to present and discuss their work. The conference will be held in a hybrid format with virtual and in-person sessions at the Tel Aviv Convention Center, Israel. 

The UMD researchers will showcase their strong presence at the international conference with 14 papers in the area of computer vision, machine learning, and graphics.

List of papers:

Temporally Consistent Semantic Video Editing

Yiran Xu, Badour AlBahar, and Jia-Bin Huang

Learning Instance-Specific Adaptation for Cross-Domain Segmentation

Yuliang Zou, Zizhao Zhang, Chun-Liang Li, Han Zhang, Tomas Pfister, and Jia-Bin Huang

Long Video Generation with Time-Agnostic VQGAN and Time-Sensitive Transformer

Songwei Ge, Thomas Hayes, Harry Yang, Xi Yin, Guan Pang, David Jacobs, Jia-Bin Huang, and Devi Parikh

Multimodal Object Detection via Probabilistic Ensembling

Yi-Ting Chen, Jinghao Shi, Zelin Ye, Christoph Mertz, Deva Ramanan, and Shu Kong

Fabric Material Recovery from Video Using Multi-Scale Geometric Auto-Encoder

J. Liang and M. C. Lin

Human Trajectory Prediction via Neural Social Physics   

J. Yue, D. Manocha, and H. Wang 

FAR: Fourier Aerial Video Recognition

D. Kothandaraman, T Guan X. Wang, S. Hu, M. C. Lin, and D. Manocha

 A Repulsive Force Unite for Garment Collision Handling in Neural Networks

Q. Tan, Y, Zhou, T. Wang, D. Ceylan, X. Sun and D. Manocha

D2-TPred: Discontinuous Dependency for Trajectory Prediction under Traffic Lights

Y. Zhang, W. Wang, W. Guo, P. Lv, M. Xu, W. Chen and D. Manocha

Improving Closed and Open Set Attribute Prediction using Transformers

K. Pham, K. Kafle, Z. Lin, Z. Ding, S. Cohen, Q. H. Tran, A. Shrivastava

 Learning Semantic Correspondence with Sparse Annotations

S. Huang, L. Yang, B. He, S. Zhang, X. He, A. Shrivastava

Neural Space-filling Curves

H. Wang, K. Gupta, L. S. Davis, A. Shrivastava

Burn After Reading: Online Adaptation for Cross-domain, Streaming Data

L. Yang, M. Gau, Z. Chen, R. Xu, A. Shrivastava, C. Ramaiah

Improving the Perceptual Quality of 2D Animation Interpolation

S. Chen, M. Zwicker