ICCV - arXivDaily 期刊&会议

2012.01377 2021-09-22 cs.CV

Cross-Descriptor Visual Localization and Mapping

Mihai Dusmanu, Ondrej Miksik, Johannes L. Schönberger, Marc Pollefeys

Comments Accepted at ICCV 2021. 18 pages, 15 figures, 6 tables

2109.09487 2021-09-21 cs.CV cs.AI cs.LG

Dyadformer: A Multi-modal Transformer for Long-Range Modeling of Dyadic Interactions

David Curto, Albert Clapés, Javier Selva, Sorina Smeureanu, Julio C. S. Jacques Junior, David Gallardo-Pujol, Georgina Guilera, David Leiva, Thomas B. Moeslund, Sergio Escalera, Cristina Palmero

Comments Accepted to the 2021 ICCV Workshop on Understanding Social Behavior in Dyadic and Small Group Interactions

2109.08901 2021-09-21 cs.LG cs.AI cs.CV

S$^3$VAADA: Submodular Subset Selection for Virtual Adversarial Active Domain Adaptation

Harsh Rangwani, Arihant Jain, Sumukh K Aithal, R. Venkatesh Babu

Comments ICCV 2021. Project page: http://sites.google.com/iisc.ac.in/s3vaada-iccv2021

2108.03673 2021-09-21 cs.CV

RECALL: Replay-based Continual Learning in Semantic Segmentation

Andrea Maracani, Umberto Michieli, Marco Toldo, Pietro Zanuttigh

Comments Accepted by ICCV 2021

2108.02774 2021-09-21 cs.CV cs.LG

Sketch Your Own GAN

Sheng-Yu Wang, David Bau, Jun-Yan Zhu

Comments ICCV 2021 website: https://peterwang512.github.io/GANSketching code: https://github.com/PeterWang512/GANSketching

2106.11539 2021-09-21 cs.CV

DocFormer: End-to-End Transformer for Document Understanding

Srikar Appalaraju, Bhavan Jasani, Bhargava Urala Kota, Yusheng Xie, R. Manmatha

Comments Accepted to ICCV 2021 main conference

2105.12441 2021-09-21 cs.LG cs.AI cs.CV

DeepGaze IIE: Calibrated prediction in and out-of-domain for state-of-the-art saliency modeling

Akis Linardos, Matthias Kümmerer, Ori Press, Matthias Bethge

Comments Joint first authors, published in ICCV

2104.05670 2021-09-21 cs.CV

Action-Conditioned 3D Human Motion Synthesis with Transformer VAE

Mathis Petrovich, Michael J. Black, Gül Varol

Comments ICCV 2021 Camera ready, 14 pages, 7 figures

2103.15042 2021-09-21 cs.CV

Distilling Virtual Examples for Long-tailed Recognition

Yin-Yin He, Jianxin Wu, Xiu-Shen Wei

Comments Accepted to ICCV 2021

2011.08932 2021-09-21 cs.CV cs.LG

Analyzing and Mitigating JPEG Compression Defects in Deep Learning

Max Ehrlich, Larry Davis, Ser-Nam Lim, Abhinav Shrivastava

Comments Accepted to the ICCV MELEX Workshop

2108.08236 2021-09-20 cs.CV cs.AI cs.LG cs.MA cs.RO

LOKI: Long Term and Key Intentions for Trajectory Prediction

Harshayu Girase, Haiming Gang, Srikanth Malla, Jiachen Li, Akira Kanehara, Karttikeya Mangalam, Chiho Choi

Comments ICCV 2021 (The dataset is available at https://usa.honda-ri.com/loki)

2108.08202 2021-09-20 eess.IV cs.CV

Overfitting the Data: Compact Neural Video Delivery via Content-aware Feature Modulation

Jiaming Liu, Ming Lu, Kaixin Chen, Xiaoqi Li, Shizun Wang, Zhaoqing Wang, Enhua Wu, Yurong Chen, Chuang Zhang, Ming Wu

Comments Accepted by ICCV 2021

2011.12663 2021-09-20 cs.CV

Bayesian Triplet Loss: Uncertainty Quantification in Image Retrieval

Frederik Warburg, Martin Jørgensen, Javier Civera, Søren Hauberg

Journal ref 2021 ICCV

2008.12066 2021-09-20 cs.CV

Minimal Adversarial Examples for Deep Learning on 3D Point Clouds

Jaeyeon Kim, Binh-Son Hua, Duc Thanh Nguyen, Sai-Kit Yeung

Comments ICCV 2021 camera-ready paper (8 pages)

2109.08141 2021-09-17 cs.CV cs.AI cs.LG

An End-to-End Transformer Model for 3D Object Detection

Ishan Misra, Rohit Girdhar, Armand Joulin

Comments Accepted at ICCV 2021

2109.08090 2021-09-17 cs.LG cs.CV

DisUnknown: Distilling Unknown Factors for Disentanglement Learning

Sitao Xiang, Yuming Gu, Pengda Xiang, Menglei Chai, Hao Li, Yajie Zhao, Mingming He

Comments Accepted for publication at ICCV 2021. Videos, demos and updates will be published at project website: https://stormraiser.github.io/disunknown/

2109.07916 2021-09-17 eess.AS cs.CV cs.HC

FSER: Deep Convolutional Neural Networks for Speech Emotion Recognition

Bonaventure F. P. Dossou, Yeno K. S. Gbenou

Comments ABAW Workshop, ICCV 2021

2109.07894 2021-09-17 cs.CV

Heterogeneous Relational Complement for Vehicle Re-identification

Jiajian Zhao, Yifan Zhao, Jia Li, Ke Yan, Yonghong Tian

Comments 10 pages, 4 figures. Accepted in ICCV 2021

2109.07554 2021-09-17 eess.IV cs.CV

A Pathology Deep Learning System Capable of Triage of Melanoma Specimens Utilizing Dermatopathologist Consensus as Ground Truth

Sivaramakrishnan Sankarapandian, Saul Kohn, Vaughn Spurrier, Sean Grullon, Rajath E. Soans, Kameswari D. Ayyagari, Ramachandra V. Chamarthi, Kiran Motaparthi, Jason B. Lee, Wonwoo Shon, Michael Bonham, Julianna D. Ianni

Comments Accepted at ICCV 2021 CDpath workshop

2109.07531 2021-09-17 cs.CV

Pose Transformers (POTR): Human Motion Prediction with Non-Autoregressive Transformers

Angel Martínez-González, Michael Villamizar, Jean-Marc Odobez

Comments Accepted in ICCV-W

2109.05591 2021-09-17 cs.CV

Multiresolution Deep Implicit Functions for 3D Shape Representation

Zhang Chen, Yinda Zhang, Kyle Genova, Sean Fanello, Sofien Bouaziz, Christian Haene, Ruofei Du, Cem Keskin, Thomas Funkhouser, Danhang Tang

Comments 8 pages of main paper, 10 pages of supplementary. Accepted by ICCV'21

2108.05054 2021-09-17 cs.CV cs.AI

Rethinking Coarse-to-Fine Approach in Single Image Deblurring

Sung-Jin Cho, Seo-Won Ji, Jun-Pyo Hong, Seung-Won Jung, Sung-Jea Ko

Comments Accepted by IEEE International Conference on Computer Vision (ICCV) 2021

2104.03916 2021-09-17 cs.CV cs.GR cs.LG

Field Convolutions for Surface CNNs

Thomas W. Mitchel, Vladimir G. Kim, Michael Kazhdan

Comments ICCV 2021 (oral), includes supplement

2008.12272 2021-09-17 cs.CV

Monocular, One-stage, Regression of Multiple 3D People

Yu Sun, Qian Bao, Wu Liu, Yili Fu, Michael J. Black, Tao Mei

Comments ICCV 2021, Code https://github.com/Arthur151/ROMP

2109.07431 2021-09-16 cs.CV cs.GR

Contact-Aware Retargeting of Skinned Motion

Ruben Villegas, Duygu Ceylan, Aaron Hertzmann, Jimei Yang, Jun Saito

Comments International Conference on Computer Vision (ICCV)

2109.07053 2021-09-16 cs.CV

Image Synthesis via Semantic Composition

Yi Wang, Lu Qi, Ying-Cong Chen, Xiangyu Zhang, Jiaya Jia

Comments Project page is at https://shepnerd.github.io/scg/. Accepted to ICCV 2021

2109.07001 2021-09-16 cs.CV

ZFlow: Gated Appearance Flow-based Virtual Try-on with 3D Priors

Ayush Chopra, Rishabh Jain, Mayur Hemani, Balaji Krishnamurthy

Comments Accepted at ICCV 2021

2109.06619 2021-09-16 cs.CV

Sampling Network Guided Cross-Entropy Method for Unsupervised Point Cloud Registration

Haobo Jiang, Yaqi Shen, Jin Xie, Jun Li, Jianjun Qian, Jian Yang

Comments Accepted by ICCV-2021

2109.03413 2021-09-16 cs.CV

YouRefIt: Embodied Reference Understanding with Language and Gesture

Yixin Chen, Qing Li, Deqian Kong, Yik Lun Kei, Song-Chun Zhu, Tao Gao, Yixin Zhu, Siyuan Huang

Comments ICCV 2021

2108.06962 2021-09-16 cs.CV

Multi-Target Adversarial Frameworks for Domain Adaptation in Semantic Segmentation

Antoine Saporta, Tuan-Hung Vu, Matthieu Cord, Patrick Pérez

Comments Accepted at the 2021 International Conference on Computer Vision (ICCV)