arXivDaily arXiv每日学术速递 周一至周五更新

期刊&会议

European Conference on Computer Vision · 会议 · Computer Vision

共收录 4823
2210.11511 2022-10-24 cs.CV cs.LG eess.IV

Overexposure Mask Fusion: Generalizable Reverse ISP Multi-Step Refinement

Jinha Kim, Jun Jiang, Jinwei Gu

Comments 15 pages, 8 figures, ECCV

详情

展开后加载摘要…

URL PDF HTML 收藏
2111.13470 2022-10-24 cs.CV

TDAM: Top-Down Attention Module for Contextually Guided Feature Selection in CNNs

Shantanu Jaiswal, Basura Fernando, Cheston Tan

Comments ECCV 2022 Camera Ready

详情

展开后加载摘要…

URL PDF HTML 收藏
2210.11204 2022-10-21 cs.CV

PalGAN: Image Colorization with Palette Generative Adversarial Networks

Yi Wang, Menghan Xia, Lu Qi, Jing Shao, Yu Qiao

Comments Accepted at ECCV 2022

详情

展开后加载摘要…

URL PDF HTML 收藏
2210.11153 2022-10-21 eess.IV cs.CV

Reversed Image Signal Processing and RAW Reconstruction. AIM 2022 Challenge Report

Marcos V. Conde, Radu Timofte, Yibin Huang, Jingyang Peng, Chang Chen, Cheng Li, Eduardo Pérez-Pellitero, Fenglong Song, Furui Bai, Shuai Liu, Chaoyu Feng, Xiaotao Wang, Lei Lei, Yu Zhu, Chenghua Li, Yingying Jiang, Yong A, Peisong Wang, Cong Leng, Jian Cheng, Xiaoyu Liu, Zhicun Yin, Zhilu Zhang, Junyi Li, Ming Liu, Wangmeng Zuo, Jun Jiang, Jinha Kim, Yue Zhang, Beiji Zou, Zhikai Zong, Xiaoxiao Liu, Juan Marín Vega, Michael Sloth, Peter Schneider-Kamp, Richard Röttger, Furkan Kınlı, Barış Özcan, Furkan Kıraç, Li Leyi, SM Nadim Uddin, Dipon Kumar Ghosh, Yong Ju Jung

Comments ECCV 2022 Advances in Image Manipulation (AIM) workshop

详情

展开后加载摘要…

URL PDF HTML 收藏
2210.11141 2022-10-21 cs.CV cs.AI

General Image Descriptors for Open World Image Retrieval using ViT CLIP

Marcos V. Conde, Ivan Aerlic, Simon Jégou

Comments ECCV 2022 Instance-Level Recognition Workshop

详情

展开后加载摘要…

URL PDF HTML 收藏
2210.11000 2022-10-21 cs.CV

Visual-Semantic Contrastive Alignment for Few-Shot Image Classification

Mohamed Afham, Ranga Rodrigo

Comments ECCV 2022 Workshop on Computer Vision in the Wild

详情

展开后加载摘要…

URL PDF HTML 收藏
2210.10820 2022-10-21 cs.CV cs.CL cs.IR cs.LG

VTC: Improving Video-Text Retrieval with User Comments

Laura Hanu, James Thewlis, Yuki M. Asano, Christian Rupprecht

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2207.09508 2022-10-21 cs.CV

HSE-NN Team at the 4th ABAW Competition: Multi-task Emotion Recognition and Learning from Synthetic Images

Andrey V. Savchenko

Comments accepted at ECCV Workshop ABAW4; 14 pages, 3 figures, 8 tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2205.06187 2022-10-21 cs.CV

Efficient Deep Visual and Inertial Odometry with Adaptive Visual Modality Selection

Mingyu Yang, Yu Chen, Hun-Seok Kim

Comments Accepted to ECCV 2022

详情

展开后加载摘要…

URL PDF HTML 收藏
2204.13631 2022-10-21 cs.CV

Reliable Visual Question Answering: Abstain Rather Than Answer Incorrectly

Spencer Whitehead, Suzanne Petryk, Vedaad Shakib, Joseph Gonzalez, Trevor Darrell, Anna Rohrbach, Marcus Rohrbach

Comments ECCV 2022. Code and models are available here: https://github.com/facebookresearch/reliable_vqa

详情

展开后加载摘要…

URL PDF HTML 收藏
2204.01403 2022-10-21 cs.CV

How stable are Transferability Metrics evaluations?

Andrea Agostinelli, Michal Pándy, Jasper Uijlings, Thomas Mensink, Vittorio Ferrari

Comments ECCV 2022

详情

展开后加载摘要…

URL PDF HTML 收藏
2203.10537 2022-10-21 cs.CV

Iwin: Human-Object Interaction Detection via Transformer with Irregular Windows

Danyang Tu, Xiongkuo Min, Huiyu Duan, Guodong Guo, Guangtao Zhai, Wei Shen

Comments Accepted to ECCV 2022

详情

展开后加载摘要…

URL PDF HTML 收藏
2110.03485 2022-10-21 cs.AI cs.CV

Cartoon Explanations of Image Classifiers

Stefan Kolek, Duc Anh Nguyen, Ron Levie, Joan Bruna, Gitta Kutyniok

Comments ECCV 2022 (oral)

详情

展开后加载摘要…

URL PDF HTML 收藏
2210.10773 2022-10-20 cs.LG cs.CV

Anomaly Detection Requires Better Representations

Tal Reiss, Niv Cohen, Eliahu Horwitz, Ron Abutbul, Yedid Hoshen

Comments Accepted to ECCV SSLWIN Workshop (2022)

详情

展开后加载摘要…

URL PDF HTML 收藏
2210.10770 2022-10-20 cs.CV

LaMAR: Benchmarking Localization and Mapping for Augmented Reality

Paul-Edouard Sarlin, Mihai Dusmanu, Johannes L. Schönberger, Pablo Speciale, Lukas Gruber, Viktor Larsson, Ondrej Miksik, Marc Pollefeys

Comments Accepted at ECCV 2022, website at https://lamar.ethz.ch/

详情

展开后加载摘要…

URL PDF HTML 收藏
2210.10758 2022-10-20 cs.CV cs.AI

GraphCSPN: Geometry-Aware Depth Completion via Dynamic GCNs

Xin Liu, Xiaofei Shao, Bo Wang, Yali Li, Shengjin Wang

Comments Accepted by ECCV 2022

详情

展开后加载摘要…

URL PDF HTML 收藏
2210.10670 2022-10-20 cs.CV cs.LG

Attaining Class-level Forgetting in Pretrained Model using Few Samples

Pravendra Singh, Pratik Mazumder, Mohammed Asad Karim

Comments Accepted in ECCV 2022

详情

展开后加载摘要…

URL PDF HTML 收藏
2210.10633 2022-10-20 cs.CV

Depth Contrast: Self-Supervised Pretraining on 3DPM Images for Mining Material Classification

Prakash Chandra Chhipa, Richa Upadhyay, Rajkumar Saini, Lars Lindqvist, Richard Nordenskjold, Seiichi Uchida, Marcus Liwicki

Comments Accepted to CVF European Conference on Computer Vision Workshop(ECCVW 2022)

详情

展开后加载摘要…

URL PDF HTML 收藏
2210.10542 2022-10-20 cs.CV

PoseGPT: Quantization-based 3D Human Motion Generation and Forecasting

Thomas Lucas, Fabien Baradel, Philippe Weinzaepfel, Grégory Rogez

Comments ECCV'22 Conference paper

详情

展开后加载摘要…

URL PDF HTML 收藏
2210.08735 2022-10-20 cs.CV

2nd Place Solution to Google Universal Image Embedding

Xiaolong Huang, Qiankun Li

Comments 3 pages, 1 figures, Instance-Level Recognition Workshop at ECCV 2022, Google Universal Image Embedding, 2nd place solution

详情

展开后加载摘要…

URL PDF HTML 收藏
2204.06607 2022-10-20 cs.CV

Towards Metrical Reconstruction of Human Faces

Wojciech Zielonka, Timo Bolkart, Justus Thies

Comments Video: https://youtu.be/vzzEbvv08VA Website: https://zielon.github.io/mica/ Accepted to ECCV 2022

详情

展开后加载摘要…

URL PDF HTML 收藏
2210.10036 2022-10-19 cs.CV

ARAH: Animatable Volume Rendering of Articulated Human SDFs

Shaofei Wang, Katja Schwarz, Andreas Geiger, Siyu Tang

Comments Accepted to ECCV 2022. Project page: https://neuralbodies.github.io/arah/

详情

展开后加载摘要…

URL PDF HTML 收藏
2210.09866 2022-10-19 cs.CV cs.LG

Towards Efficient and Effective Self-Supervised Learning of Visual Representations

Sravanti Addepalli, Kaushal Bhogale, Priyam Dey, R. Venkatesh Babu

Comments ECCV 2022

详情

展开后加载摘要…

URL PDF HTML 收藏
2210.09852 2022-10-19 cs.LG cs.CR cs.CV stat.ML

Scaling Adversarial Training to Large Perturbation Bounds

Sravanti Addepalli, Samyak Jain, Gaurang Sriramanan, R. Venkatesh Babu

Comments ECCV 2022

详情

展开后加载摘要…

URL PDF HTML 收藏
2210.09615 2022-10-19 cs.CV

Homogeneous Multi-modal Feature Fusion and Interaction for 3D Object Detection

Xin Li, Botian Shi, Yuenan Hou, Xingjiao Wu, Tianlong Ma, Yikang Li, Liang He

Comments Accepted by ECCV 2022

详情

展开后加载摘要…

URL PDF HTML 收藏
2210.09267 2022-10-19 cs.CV cs.LG cs.RO

CramNet: Camera-Radar Fusion with Ray-Constrained Cross-Attention for Robust 3D Object Detection

Jyh-Jing Hwang, Henrik Kretzschmar, Joshua Manela, Sean Rafferty, Nicholas Armstrong-Crews, Tiffany Chen, Dragomir Anguelov

Comments ECCV 2022

详情

展开后加载摘要…

URL PDF HTML 收藏
2210.08391 2022-10-19 cs.CV

Video in 10 Bits: Few-Bit VideoQA for Efficiency and Privacy

Shiyuan Huang, Robinson Piramuthu, Shih-Fu Chang, Gunnar A. Sigurdsson

Comments ECCV Workshop 2022

详情

展开后加载摘要…

URL PDF HTML 收藏
2210.01917 2022-10-19 cs.CV cs.RO

Differentiable Raycasting for Self-supervised Occupancy Forecasting

Tarasha Khurana, Peiyun Hu, Achal Dave, Jason Ziglar, David Held, Deva Ramanan

Comments ECCV 2022. Code available at https://github.com/tarashakhurana/emergent-occ-forecasting

详情

展开后加载摘要…

URL PDF HTML 收藏
2210.09234 2022-10-18 cs.CV cs.AI

Improving Contrastive Learning on Visually Homogeneous Mars Rover Images

Isaac Ronald Ward, Charles Moore, Kai Pak, Jingdao Chen, Edwin Goh

Comments Accepted at the AI4Space 2022 Workshop at ECCV 2022

详情

展开后加载摘要…

URL PDF HTML 收藏
2210.09204 2022-10-18 cs.CV

ArtFacePoints: High-resolution Facial Landmark Detection in Paintings and Prints

Aline Sindel, Andreas Maier, Vincent Christlein

Comments 16 pages, 8 figures, 3 tables, accepted to VISART workshop at ECCV 2022

详情

展开后加载摘要…

URL PDF HTML 收藏