ECCV

Panoramic Human Activity Recognition

Ruize Han, Haomin Yan, Jiacheng Li, Songmiao Wang, Wei Feng, Song Wang

Comments 17 pages

Journal ref European Conference on Computer Vision (ECCV 2022)

Soft Masking for Cost-Constrained Channel Pruning

Ryan Humble, Maying Shen, Jorge Albericio Latorre, Eric Darve1, Jose M. Alvarez

Comments Accepted by ECCV 2022

Large Scale Real-World Multi-Person Tracking

Bing Shuai, Alessandro Bergamo, Uta Buechler, Andrew Berneshawi, Alyssa Boden, Joseph Tighe

Comments ECCV 2022

Abstract Images Have Different Levels of Retrievability Per Reverse Image Search Engine

Shawn M. Jones, Diane Oyen

Comments 20 pages; 7 figures; to be published in the proceedings of the Drawings and abstract Imagery: Representation and Analysis (DIRA) Workshop from ECCV 2022

Multi-Faceted Distillation of Base-Novel Commonality for Few-shot Object Detection

Shuang Wu, Wenjie Pei, Dianwen Mei, Fanglin Chen, Jiandong Tian, Guangming Lu

Comments Accepted to ECCV 2022

What to Hide from Your Students: Attention-Guided Masked Image Modeling

Ioannis Kakogeorgiou, Spyros Gidaris, Bill Psomas, Yannis Avrithis, Andrei Bursuc, Konstantinos Karantzalos, Nikos Komodakis

Comments ECCV 2022. Codes and models are available at https://github.com/gkakogeorgiou/attmask

Journal ref European Conference on Computer Vision (2022)

DEArt: Dataset of European Art

Artem Reshetnikov, Maria-Cristina Marinescu, Joaquim More Lopez

Comments VISART VI. Workshop at the European Conference of Computer Vision (ECCV)

Generative Poisoning Using Random Discriminators

Dirren van Vlijmen, Alex Kolmus, Zhuoran Liu, Zhengyu Zhao, Martha Larson

Comments 6 pages, 2 figures, 4 tables, accepted as an oral presentation at RCV (ECCV 2022 Workshop)

Understanding Collapse in Non-Contrastive Siamese Representation Learning

Alexander C. Li, Alexei A. Efros, Deepak Pathak

Comments Published at ECCV 2022. Project page at https://alexanderli.com/noncontrastive-ssl/

Uncertainty-DTW for Time Series and Sequences

Lei Wang, Piotr Koniusz

Comments Accepted as an oral paper at the 17th European Conference on Computer Vision (ECCV 2022). arXiv admin note: text overlap with arXiv:2210.16820

Max Pooling with Vision Transformers reconciles class and shape in weakly supervised semantic segmentation

Simone Rossetti, Damiano Zappia, Marta Sanzari, Marco Schaerf, Fiora Pirri

Comments 28 pages, 9 images, ECCV 2022 conference

Generative Negative Text Replay for Continual Vision-Language Pretraining

Shipeng Yan, Lanqing Hong, Hang Xu, Jianhua Han, Tinne Tuytelaars, Zhenguo Li, Xuming He

Comments ECCV 2022

Time-rEversed diffusioN tEnsor Transformer: A new TENET of Few-Shot Object Detection

Shan Zhang, Naila Murray, Lei Wang, Piotr Koniusz

Comments Accepted at the 17th European Conference on Computer Vision (ECCV 2022)

Multi-Person 3D Pose and Shape Estimation via Inverse Kinematics and Refinement

Junuk Cha, Muhammad Saqlain, GeonU Kim, Mingyu Shin, Seungryul Baek

Comments Published at ECCV 2022

Graph2Vid: Flow graph to Video Grounding for Weakly-supervised Multi-Step Localization

Nikita Dvornik, Isma Hadji, Hai Pham, Dhaivat Bhatt, Brais Martinez, Afsaneh Fazly, Allan D. Jepson

Comments ECCV'22, oral

Journal ref ECCV 2022

CADyQ: Content-Aware Dynamic Quantization for Image Super-Resolution

Cheeun Hong, Sungyong Baik, Heewon Kim, Seungjun Nah, Kyoung Mu Lee

Comments ECCV 2022

Open-world Semantic Segmentation via Contrasting and Clustering Vision-Language Embedding

Quande Liu, Youpeng Wen, Jianhua Han, Chunjing Xu, Hang Xu, Xiaodan Liang

Comments Accepted to ECCV 2022 (revise acknowledgement)

DeepShadow: Neural Shape from Shadow

Asaf Karnieli, Ohad Fried, Yacov Hel-Or

Comments ECCV 2022. Project page available at https://asafkar.github.io/deepshadow/

SocialVAE: Human Trajectory Prediction using Timewise Latents

Pei Xu, Jean-Bernard Hayet, Ioannis Karamouzas

Comments In the 17th European Conference on Computer Vision (ECCV 2022). Code: https://github.com/xupei0610/SocialVAE

Journal ref Computer Vision -- ECCV 2022. ECCV 2022. Lecture Notes in Computer Science, vol 13664, page 511--528

Adaptive Mask-based Pyramid Network for Realistic Bokeh Rendering

Konstantinos Georgiadis, Albert Saà-Garriga, Mehmet Kerim Yucel, Anastasios Drosou, Bruno Manganelli

Comments ECCV 2022 Advances in Image Manipulation Workshop. See the workshop website for posters and recordings

Bridging the visual gap in VLN via semantically richer instructions

Joaquin Ossandón, Benjamin Earle, Álvaro Soto

Comments Accepted in ECCV 2022. Research completed on November 21, 2021

Addressing Heterogeneity in Federated Learning via Distributional Transformation

Haolin Yuan, Bo Hui, Yuchen Yang, Philippe Burlina, Neil Zhenqiang Gong, Yinzhi Cao

Comments In the Proceedings of European Conference on Computer Vision (ECCV), 2022

Decoupled Mixup for Generalized Visual Recognition

Haozhe Liu, Wentian Zhang, Jinheng Xie, Haoqian Wu, Bing Li, Ziqi Zhang, Yuexiang Li, Yawen Huang, Bernard Ghanem, Yefeng Zheng

Comments Accepted by ECCV'2022 Workshop: Causality in Vision

Image Super-Resolution With Deep Variational Autoencoders

Darius Chira, Ilian Haralampiev, Ole Winther, Andrea Dittadi, Valentin Liévin

Comments ECCV 2022 Workshop on Advances in Image Manipulation

Pointly-Supervised Panoptic Segmentation

Junsong Fan, Zhaoxiang Zhang, Tieniu Tan

Comments Accepted to ECCV 2022

SUPR: A Sparse Unified Part-Based Human Representation

Ahmed A. A. Osman, Timo Bolkart, Dimitrios Tzionas, Michael J. Black

Comments Accepted in ECCV 2022

Towards an Error-free Deep Occupancy Detector for Smart Camera Parking System

Tung-Lam Duong, Van-Duc Le, Tien-Cuong Bui, Hai-Thien To

Comments Paper got accepted to Oral ECCV workshop (CVCIE)

Neural Color Operators for Sequential Image Retouching

Yili Wang, Xin Li, Kun Xu, Dongliang He, Qi Zhang, Fu Li, Errui Ding

Comments Accepted to ECCV 2022. Code is available at https://github.com/amberwangyili/neurop

RTMV: A Ray-Traced Multi-View Synthetic Dataset for Novel View Synthesis

Jonathan Tremblay, Moustafa Meshry, Alex Evans, Jan Kautz, Alexander Keller, Sameh Khamis, Thomas Müller, Charles Loop, Nathan Morrical, Koki Nagano, Towaki Takikawa, Stan Birchfield

Comments ECCV 2022 Workshop on Learning to Generate 3D Shapes and Scenes. Project page at http://www.cs.umd.edu/~mmeshry/projects/rtmv

PseudoAugment: Learning to Use Unlabeled Data for Data Augmentation in Point Clouds

Zhaoqi Leng, Shuyang Cheng, Benjamin Caine, Weiyue Wang, Xiao Zhang, Jonathon Shlens, Mingxing Tan, Dragomir Anguelov

Journal ref ECCV 2022 (pp. 555-572). Springer, Cham