Ultra-Efficient On-Device Object Detection on AI-Integrated Smart Glasses with TinyissimoYOLO
机构 * ETH Zürich（苏黎世联邦理工学院） ； University of Bologna（博洛尼亚大学）
Comments This paper has been accepted for publication at ECCV 2024 Workshops, Milan, 2024
期刊&会议
ECCV
European Conference on Computer Vision · 会议 · Computer Vision
Continual Action Quality Assessment via Adaptive Manifold-Aligned Graph Regularization
机构 * Department of Psychological and Cognitive Sciences, Tsinghua University（心理与认知科学系，清华大学） ； Institute for AI, BNRist Center, Tsinghua-Bosch Joint ML Center, THBI Lab, Tsinghua University（人工智能研究院、北京人工智能研究所、清华大学-博世联合机器学习中心、THBI实验室，清华大学） ； Department of Computer Science, Durham University（计算机科学系，杜尔姆大学） ； State Key Laboratory of Virtual Reality Technology and Systems, Beihang University（虚拟现实技术与系统国家重点实验室，北京航空航天大学） ； Zhongguancun Laboratory, Beijing（中关村实验室，北京）
Comments Extended Version of MAGR (ECCV 2024 Oral Presentation)
Drone Detection Using a Low-Power Neuromorphic Virtual Tripwire
机构 * Swedish Defence Research Agency (FOI)（瑞典国防研究机构（FOI））
Journal ref ECCV 2024 Workshops. ECCV 2024. Lecture Notes in Computer Science, vol 15646. Springer, Cham
Closed-Loop Unsupervised Representation Disentanglement with $β$-VAE Distillation and Diffusion Probabilistic Feedback
机构 * Ningbo Institute of Digital Twin, Eastern Institute of Technology（宁波数字孪生研究所、东部技术研究所） ； Shanghai Jiao Tong University（上海交通大学） ； Xi’an Jiaotong University（西安交通大学）
Comments ECCV 2024
Evidential Transformers for Improved Image Retrieval
机构 * ETH Zürich（苏黎世联邦理工学院） ； Texas A&M University（德克萨斯大学）
Comments 6 pages, 6 figures, presented at the 3rd Workshop on Uncertainty Quantification for Computer Vision, at the ECCV 2024 conference in Milan, Italy
Image-guided topic modeling for interpretable privacy classification
Comments Paper accepted at the eXCV Workshop at ECCV 2024. Supplementary material included. Code available at https://github.com/idiap/itm
PointFix: Learning to Fix Domain Bias for Robust Online Stereo Adaptation
机构 * Yonsei University（延世大学） ； NAVER AI Lab（NAVER AI实验室） ； Ewha Womans University（成均馆大学）
Comments Accepted to ECCV 2022
AnoVox: A Benchmark for Multimodal Anomaly Detection in Autonomous Driving
机构 * FZI Research Center for Information Technology（弗劳恩霍夫研究所信息技术研究中心） ； Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院） ； Technical University of Berlin（柏林技术大学）
Comments Daniel Bogdoll, Iramm Hamdard, and Lukas Namgyu Rößler contributed equally. Accepted for publication at ECCV 2024 W-CODA workshop
On Spectral Properties of Gradient-based Explanation Methods
机构 * Department of Computer Science, Royal Institute of Technology（计算机科学系，皇家理工学院）
Comments 36 pages, 16 figures, published in European Conference on Computer Vision 2024
Journal ref ECCV 2024, LNCS 15145, pp. 282-299
Open-Set Biometrics: Beyond Good Closed-Set Models
机构 * Michigan State University（密歇根州立大学）
Comments Published at ECCV 2024
PointRegGPT: Boosting 3D Point Cloud Registration using Generative Point-Cloud Pairs for Training
机构 * University of Electronic Science and Technology of China（电子科技大学） ； The Chinese University of Hong Kong（香港中文大学） ； Hong Kong University of Science and Technology（香港科技大学） ； Megvii Technology（商汤科技）
Comments To appear at the European Conference on Computer Vision (ECCV) 2024
Model Stock: All we need is just a few fine-tuned models
机构 * NAVER AI Lab（NAVER人工智能实验室）
Comments ECCV 2024 oral presenetation; Code at https://github.com/naver-ai/model-stock
Art2Mus: Bridging Visual Arts and Music through Cross-Modal Generation
机构 * Department of Computer Science, University of Bari Aldo Moro, Italy（巴里阿尔多·莫罗大学计算机科学系）
Comments Presented at the AI for Visual Arts (AI4VA) workshop at ECCV 2024
DreamScene: 3D Gaussian-based End-to-end Text-to-3D Scene Generation
机构 * University of Science and Technology of China（中国科学技术大学） ； Nanyang Technological University（南洋理工大学） ； Hong Kong University of Science and Technology（香港科学理工大学） ； University of Helsinki（赫尔辛基大学） ； Aarhus University（奥胡斯大学）
Comments Extended version of ECCV 2024 paper "DreamScene"
Motion Keyframe Interpolation for Any Human Skeleton via Temporally Consistent Point Cloud Sampling and Reconstruction
机构 * The University of Sydney（悉尼大学） ； Meta Reality Labs（Meta现实实验室）
Comments Published in ECCV 2024
Context Diffusion: In-Context Aware Image Generation
机构 * Meta GenAI（Meta 生成式人工智能） ； University of Amsterdam（阿姆斯特丹大学）
Journal ref European Conference on Computer Vision (ECCV) 2024
A Simple Low-bit Quantization Framework for Video Snapshot Compressive Imaging
机构 * Zhejiang University（浙江大学） ； School of Engineering, Westlake University（西湖大学工程学院）
Comments 18 pages, Accepted by ECCV 2024
SparseRadNet: Sparse Perception Neural Network on Subsampled Radar Data
机构 * University of Wuppertal（乌珀塔尔大学） ； Aptiv Services Deutschland GmbH（Aptiv Services德国公司）
Comments 18 pages, 4 figures, 5 tables, with supplement
Journal ref European Conference on Computer Vision, 2024: 52-69
Image Translation with Kernel Prediction Networks for Semantic Segmentation
机构 * Stony Brook University（石溪大学） ； Microsoft Corporation（微软公司）
Comments OOD-CV Workshop at ECCV 2024
CoPT: Unsupervised Domain Adaptive Segmentation using Domain-Agnostic Text Embeddings
机构 * Stony Brook University（石溪大学）
Comments ECCV 2024
Self-Rectifying Diffusion Sampling with Perturbed-Attention Guidance
机构 * Korea University（韩国大学） ； Samsung Electronics（三星电子）
Comments Project page is available at https://ku-cvlab.github.io/Perturbed-Attention-Guidance. This version reflects the ECCV 2024 camera-ready submission
ECCV 2024 W-CODA: 1st Workshop on Multimodal Perception and Comprehension of Corner Cases in Autonomous Driving
机构 * Hong Kong University of Science and Technology（香港科学与技术大学） ； The Chinese University of Hong Kong（香港中文大学） ； Dalian University of Technology（大连理工大学） ； TU Delft（代尔夫特理工大学） ； Huawei Noah’s Ark Lab（华为诺亚实验室） ； Huawei Zurich Research Center（华为苏黎世研究中心） ； Huawei IAS BU（华为IAS业务单元）
Comments ECCV 2024. Workshop page: https://coda-dataset.github.io/w-coda2024/
Enhanced Controllability of Diffusion Models via Feature Disentanglement and Realism-Enhanced Sampling Methods
机构 * Purdue University（普渡大学） ； Adobe Applied Research（Adobe应用研究） ； Adobe Research（Adobe研究）
Comments ECCV 2024; Code is available at https://github.com/WonwoongCho/Towards-Enhanced-Controllability-of-Diffusion-Models
Towards Efficient Exemplar Based Image Editing with Multimodal VLMs
机构 * Indian Institute of Technology, Bombay（印度理工学院班加罗尔分校） ； Indian Institute of Technology, Roorkee（印度理工学院罗尔基分校） ； Microsoft Research（微软研究院） ； Stanford University（斯坦福大学） ； Adobe MDSR（Adobe MDSR实验室） ； Carnegie Mellon University（卡内基梅隆大学）
Comments Accepted at ECCV 2024 (AI4VA Workshop)
Visual Prompt Engineering for Vision Language Models in Radiology
机构 * Division of Medical Image Computing, German Cancer Research Center, Heidelberg, Germany（德国癌症研究中心医学图像计算部） ； Faculty of Mathematics and Computer Science, Heidelberg University, Heidelberg, Germany（海德堡大学数学与计算机科学学院） ； Medical Faculty Heidelberg, University of Heidelberg, Heidelberg, Germany（海德堡大学医学学院）
Comments Accepted at ECCV 2024 Workshop on Emergent Visual Abilities and Limits of Foundation Models & Medical Imaging with Deep Learning 2025
Fast Point Cloud Geometry Compression with Context-based Residual Coding and INR-based Refinement
机构 * McMaster University（麦克斯特大学） ； Shanghai Jiao Tong University（上海交通大学）
Comments Accepted by ECCV 2024. Code available at: https://github.com/hxu160/CRCIR_for_PCGC
LRSLAM: Low-rank Representation of Signed Distance Fields in Dense Visual SLAM System
机构 * Dept of Computer Science and Engineering, Korea University, Seoul, Korea（韩国大学计算机科学与工程系） ； Dept of Electrical and Electronic Engineering, Yonsei University, Seoul, Korea（延世大学电气与电子工程系） ； Meta Reality Labs, Pittsburgh, PA 15222, USA（Meta Reality Labs）
Comments Accepted at ECCV 2024
A Probability-guided Sampler for Neural Implicit Surface Rendering
机构 * Mitsubishi Electric Research Laboratories (MERL), Cambridge Instituto Superior T\'ecnico, Universidade de Lisboa Toyota Research Institute, Los Altos
Comments Accepted in ECCV 2024
Journal ref European Conference on Computer Vision 2024 (pp. 164-182)
RMT-BVQA: Recurrent Memory Transformer-based Blind Video Quality Assessment for Enhanced Video Content
机构 * Visual Information Laboratory, University of Bristol（布里斯托大学视觉信息实验室） ； Amazon Prime Video（亚马逊Prime视频）
Comments This paper has been accepted by the ECCV 2024 AIM Advances in Image Manipulation workshop
Mixed Non-linear Quantization for Vision Transformers
机构 * Chungnam National University（Chungnam国立大学） ； Electronics and Telecommunications Research Institute（电子电信研究所） ； Korea Electronics Technology Institute（韩国电子技术研究所）
Comments 16 pages, 4 figures, Accepted in ECCV Workshops 2024
