ECCV

Trapped in texture bias? A large scale comparison of deep instance segmentation

Johannes Theodoridis, Jessica Hofmann, Johannes Maucher, Andreas Schilling

Comments Accepted at ECCV 2022. Code: https://github.com/JohannesTheo/trapped-in-texture-bias

Journal ref ECCV 2022 17th European Conference, Tel Aviv, Israel, October 23-27, 2022, Proceedings, Part VIII. Springer-Verlag, Berlin, Heidelberg, 609-627

Color-$S^{4}L$: Self-supervised Semi-supervised Learning with Image Colorization

Hanxiao Chen

Comments This original work has been accepted and presented in the Poster Session at ECCV 2020 WiCV Workshop. (https://sites.google.com/view/wicvworkshop-eccv2020/program/presentations)

ECCV Caption: Correcting False Negatives by Collecting Machine-and-Human-verified Image-Caption Associations for MS-COCO

Sanghyuk Chun, Wonjae Kim, Song Park, Minsuk Chang, Seong Joon Oh

Comments Published in ECCV 2022; 32 pages (2.3MB); Code and dataset: https://github.com/naver-ai/eccv-caption; v5 fixes errors in Table 4: the COCO 1K R@1 numbers were incorrect. All other tables and figures are correct. v5 also adds RSUM scores in Tab 4 and 5: RSUM has a high correlation with COCO 1K recalls; v4 fixes errors in v3 -- see the v4 comment for details

UnionDet: Union-Level Detector Towards Real-Time Human-Object Interaction Detection

Bumsoo Kim, Taeho Choi, Jaewoo Kang, Hyunwoo J. Kim

Comments ECCV 2020

Fast-ParC: Capturing Position Aware Global Feature for ConvNets and ViTs

Tao Yang, Haokui Zhang, Wenze Hu, Changwen Chen, Xiaoyu Wang

Comments 22 pages, 8 figures, 10 tables. A preliminary version of this paper has been published in ECCV 2022 and it can be find in arXiv:2203.03952

ModSelect: Automatic Modality Selection for Synthetic-to-Real Domain Generalization

Zdravko Marinov, Alina Roitberg, David Schneider, Rainer Stiefelhagen

Comments 14 pages, 6 figures, Accepted at ECCV 2022 OOD workshop

Real-Time Under-Display Cameras Image Restoration and HDR on Mobile Devices

Marcos V. Conde, Florin Vasluianu, Sabari Nathan, Radu Timofte

Comments ECCV 2022 AIM Workshop. arXiv admin note: text overlap with arXiv:2210.13552

Box2Mask: Weakly Supervised 3D Semantic Instance Segmentation Using Bounding Boxes

Julian Chibane, Francis Engelmann, Tuan Anh Tran, Gerard Pons-Moll

Comments Project page: https://virtualhumans.mpi-inf.mpg.de/box2mask/

Journal ref European Conference on Computer Vision (ECCV), 2022, Oral Presentation

CHORE: Contact, Human and Object REconstruction from a single RGB image

Xianghui Xie, Bharat Lal Bhatnagar, Gerard Pons-Moll

Comments Accepted at ECCV 2022, edited the acknowledgement

Intel Labs at Ego4D Challenge 2022: A Better Baseline for Audio-Visual Diarization

Kyle Min

Comments Validation report for the Ego4D challenge at ECCV 2022

Vision-Language Adaptive Mutual Decoder for OOV-STR

Jinshui Hu, Chenyu Liu, Qiandong Yan, Xuyang Zhu, Jiajia Wu, Jun Du, Lirong Dai

Comments 1st Place Solution to ECCV 2022 OOV-ST Challenge; ICIG 2023

Hierarchical Memory Learning for Fine-Grained Scene Graph Generation

Youming Deng, Yansheng Li, Yongjun Zhang, Xiang Xiang, Jian Wang, Jingdong Chen, Jiayi Ma

Comments ECCV 2022

RFNet-4D++: Joint Object Reconstruction and Flow Estimation from 4D Point Clouds with Cross-Attention Spatio-Temporal Features

Tuan-Anh Vu, Duc Thanh Nguyen, Binh-Son Hua, Quang-Hieu Pham, Sai-Kit Yeung

Comments TPAMI journal extension of ECCV 2022 arXiv:2203.16482

Compound Prototype Matching for Few-shot Action Recognition

Yifei Huang, Lijin Yang, Yoichi Sato

Comments ECCV 2022

Dual-Stream Knowledge-Preserving Hashing for Unsupervised Video Retrieval

Pandeng Li, Hongtao Xie, Jiannan Ge, Lei Zhang, Shaobo Min, Yongdong Zhang

Comments 17 pages, 8 figures, ECCV 2022

MemSAC: Memory Augmented Sample Consistency for Large Scale Unsupervised Domain Adaptation

Tarun Kalluri, Astuti Sharma, Manmohan Chandraker

Comments Accepted at ECCV 2022. Project Webpage: https://tarun005.github.io/MemSAC/

VLANet: Video-Language Alignment Network for Weakly-Supervised Video Moment Retrieval

Minuk Ma, Sunjae Yoon, Junyeong Kim, Youngjoon Lee, Sunghun Kang, Chang D. Yoo

Comments 16 pages, 6 figures, European Conference on Computer Vision, 2020

ReLER@ZJU Submission to the Ego4D Moment Queries Challenge 2022

Jiayi Shao, Xiaohan Wang, Yi Yang

Comments Accepted to ECCV 2022 Ego4D Workshop; 3rd place in Ego4D Moment Query Challenge

Spatial and Visual Perspective-Taking via View Rotation and Relation Reasoning for Embodied Reference Understanding

Cheng Shi, Sibei Yang

Comments ECCV 2022. Code: http://github.com/ChengShiest/REP-ERU

STEm-Seg: Spatio-temporal Embeddings for Instance Segmentation in Videos

Ali Athar, Sabarinath Mahadevan, Aljoša Ošep, Laura Leal-Taixé, Bastian Leibe

Comments ECCV 2020 28 pages, 6 figures

Learning Prior Feature and Attention Enhanced Image Inpainting

Chenjie Cao, Qiaole Dong, Yanwei Fu

Comments ECCV 2022

Unsupervised Selective Labeling for More Effective Semi-Supervised Learning

Xudong Wang, Long Lian, Stella X. Yu

Comments Accepted by ECCV 2022; Fixed a few typos

SegPGD: An Effective and Efficient Adversarial Attack for Evaluating and Boosting Segmentation Robustness

Jindong Gu, Hengshuang Zhao, Volker Tresp, Philip Torr

Journal ref European Conference on Computer Vision (ECCV) , 2022

Gradient-based Uncertainty for Monocular Depth Estimation

Julia Hornauer, Vasileios Belagiannis

Comments Accepted to ECCV 2022

MFIM: Megapixel Facial Identity Manipulation

Sanghyeon Na

Comments ECCV 2022 accepted

S$^2$Contact: Graph-based Network for 3D Hand-Object Contact Estimation with Semi-Supervised Learning

Tze Ho Elden Tse, Zhongqun Zhang, Kwang In Kim, Ales Leonardis, Feng Zheng, Hyung Jin Chang

Comments Accepted to ECCV 2022

Multi-Granularity Prediction with Learnable Fusion for Scene Text Recognition

Cheng Da, Peng Wang, Cong Yao

Comments submitted to TPAMI; an extension to our previous ECCV 2022 paper arXiv:2209.03592

AdaBest: Minimizing Client Drift in Federated Learning via Adaptive Bias Estimation

Farshid Varno, Marzie Saghayi, Laya Rafiee Sevyeri, Sharut Gupta, Stan Matwin, Mohammad Havaei

Comments Published as a conference paper at ECCV 2022; Corrected some typos in the text and a baseline algorithm

Feed-Forward Source-Free Domain Adaptation via Class Prototypes

Ondrej Bohdal, Da Li, Timothy Hospedales

Comments ECCV 2022 Workshop on Out of Distribution Generalization in Computer Vision (OOD-CV)

APRICOT: A Dataset of Physical Adversarial Attacks on Object Detection

Anneliese Braunegg, Amartya Chakraborty, Michael Krumdick, Nicole Lape, Sara Leary, Keith Manville, Elizabeth Merkhofer, Laura Strickhart, Matthew Walmer

Comments 23 pages, 14 figures, 3 tables. Updated version as accepted to ECCV 2020