2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)最新文献

Plots to Previews: Towards Automatic Movie Preview Retrieval using Publicly Available Meta-data 图到预览:利用公开可用的元数据实现电影预览的自动检索

2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW) Pub Date : 2021-10-01 DOI: 10.1109/ICCVW54120.2021.00359

Bhagyashree Gaikwad, Ankit Sontakke, Manasi S. Patwardhan, N. Pedanekar, S. Karande

{"title":"Plots to Previews: Towards Automatic Movie Preview Retrieval using Publicly Available Meta-data","authors":"Bhagyashree Gaikwad, Ankit Sontakke, Manasi S. Patwardhan, N. Pedanekar, S. Karande","doi":"10.1109/ICCVW54120.2021.00359","DOIUrl":"https://doi.org/10.1109/ICCVW54120.2021.00359","url":null,"abstract":"‘Preview’, a concept popularized by Netflix, is a contiguous scene of a movie or a TV show highlighting its story, characters, and tone, thus helping viewers to make quick viewing decisions. To create previews, one needs scenelevel semantic annotations related to the story, characters, and tone. Soliciting such annotations is an involved exercise and these are expensive to generate automatically. Instead, we aim at creating previews by availing readily available scene meta-data, while avoiding dependency on semantic scene-level annotations. We hypothesize that movie scenes that best match publicly available IMDb plot summaries can make good previews. We use 51 movies from the MovieGraph dataset, and find that a match of the plot summaries with scene dialogues, available through subtitles, is adequate to create usable movie previews, without the need for other semantic annotations. We validate the hypothesis by comparing ratings for scenes selected by the proposed method to those for scenes selected randomly, obtained from regular viewers as well as an expert. We report that even with this ‘minimalist’ approach, we can select at least one good preview scene for 26 out of 51 movies, as agreed upon by a critical expert judgment. Error analysis of the scenes indicates that features related to the plot structure might be needed to further improve the results.","PeriodicalId":226794,"journal":{"name":"2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)","volume":"110 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115697050","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 3

Balanced Masked and Standard Face Recognition 平衡蒙面和标准人脸识别

2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW) Pub Date : 2021-10-01 DOI: 10.1109/ICCVW54120.2021.00174

Delong Qi, Kangli Hu, Weijun Tan, Qi Yao, Jingfeng Liu

引用次数: 3

Predictive Coding with Topographic Variational Autoencoders 预测编码与地形变分自编码器

2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW) Pub Date : 2021-10-01 DOI: 10.1109/ICCVW54120.2021.00127

Thomas Anderson Keller, M. Welling

引用次数: 2

The 2nd Challenge on Remote Physiological Signal Sensing (RePSS) 远程生理信号传感(RePSS)的第二次挑战

2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW) Pub Date : 2021-10-01 DOI: 10.1109/ICCVW54120.2021.00273

Xiaobai Li, Haomiao Sun, Zhaodong Sun, Hu Han, A. Dantcheva, S. Shan, Guoying Zhao

引用次数: 3

PP-NAS: Searching for Plug-and-Play Blocks on Convolutional Neural Network PP-NAS:在卷积神经网络上搜索即插即用块

2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW) Pub Date : 2021-10-01 DOI: 10.1109/ICCVW54120.2021.00045

Biluo Shen, Anqi Xiao, Jie Tian, Z. Hu

引用次数: 1

Efficient Uncertainty Estimation in Semantic Segmentation via Distillation 基于蒸馏的语义分割的高效不确定性估计

2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW) Pub Date : 2021-10-01 DOI: 10.1109/ICCVW54120.2021.00343

Christopher J. Holder, M. Shafique

{"title":"Efficient Uncertainty Estimation in Semantic Segmentation via Distillation","authors":"Christopher J. Holder, M. Shafique","doi":"10.1109/ICCVW54120.2021.00343","DOIUrl":"https://doi.org/10.1109/ICCVW54120.2021.00343","url":null,"abstract":"Deep neural networks typically make predictions with little regard for the probability that a prediction might be incorrect. Attempts to address this often involve input data undergoing multiple forward passes, either of multiple models or of multiple configurations of a single model, and consensus among outputs is used as a measure of confidence. This can be computationally expensive, as the time taken to process a single input sample increases linearly with the number of output samples being generated, an important consideration in real-time scenarios such as autonomous driving, and so we propose Uncertainty Distillation as a more efficient method for quantifying prediction uncertainty. Inspired by the concept of Knowledge Distillation, whereby the performance of a compact model is improved by training it to mimic the outputs of a larger model, we train a compact model to mimic the output distribution of a large ensemble of models, such that for each output there is a prediction and a predicted level of uncertainty for that prediction. We apply Uncertainty Distillation in the context of a semantic segmentation task for autonomous vehicle scene understanding and demonstrate a capability to reliably predict pixelwise uncertainty over the resultant class probability map. We also show that the aggregate pixel uncertainty across an image can be used as a metric for reliable detection of out-of-distribution data.","PeriodicalId":226794,"journal":{"name":"2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)","volume":"112 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117278273","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 12

Synthetic Temporal Anomaly Guided End-to-End Video Anomaly Detection 合成时间异常引导端到端视频异常检测

2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW) Pub Date : 2021-10-01 DOI: 10.1109/ICCVW54120.2021.00028

M. Astrid, M. Zaheer, Seung-Ik Lee

引用次数: 20

Progressive Unsupervised Deep Transfer Learning for Forest Mapping in Satellite Image 基于渐进式无监督深度迁移学习的卫星图像森林映射

2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW) Pub Date : 2021-10-01 DOI: 10.1109/ICCVW54120.2021.00089

Nouman Ahmed, Sudipan Saha, M. Shahzad, M. Fraz, Xiao Xiang Zhu

{"title":"Progressive Unsupervised Deep Transfer Learning for Forest Mapping in Satellite Image","authors":"Nouman Ahmed, Sudipan Saha, M. Shahzad, M. Fraz, Xiao Xiang Zhu","doi":"10.1109/ICCVW54120.2021.00089","DOIUrl":"https://doi.org/10.1109/ICCVW54120.2021.00089","url":null,"abstract":"Automated forest mapping is important to understand our forests that play a key role in ecological system. However, efforts towards forest mapping is impeded by difficulty to collect labeled forest images that show large intraclass variation. Recently unsupervised learning has shown promising capability when exploiting limited labeled data. Motivated by this, we propose a progressive unsupervised deep transfer learning method for forest mapping. The proposed method exploits a pre-trained model that is subsequently fine-tuned over the target forest domain. We propose two different fine-tuning mechanism, one works in a totally unsupervised setting by jointly learning the parameters of CNN and the k-means based cluster assignments of the resulting features and the other one works in a semi-supervised setting by exploiting the extracted knearest neighbor based pseudo labels. The proposed progressive scheme is evaluated on publicly available EuroSAT dataset using the relevant base model trained on BigEarthNet labels. The results show that the proposed method greatly improves the forest regions classification accuracy as compared to the unsupervised baseline, nearly approaching the supervised classification approach.","PeriodicalId":226794,"journal":{"name":"2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125054679","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

UAC: An Uncertainty-Aware Face Clustering Algorithm 一种不确定性感知人脸聚类算法

2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW) Pub Date : 2021-10-01 DOI: 10.1109/ICCVW54120.2021.00388

Biplob K. Debnath, G. Coviello, Yi Yang, S. Chakradhar

{"title":"UAC: An Uncertainty-Aware Face Clustering Algorithm","authors":"Biplob K. Debnath, G. Coviello, Yi Yang, S. Chakradhar","doi":"10.1109/ICCVW54120.2021.00388","DOIUrl":"https://doi.org/10.1109/ICCVW54120.2021.00388","url":null,"abstract":"We investigate ways to leverage uncertainty in face images to improve the quality of the face clusters. We observe that popular clustering algorithms do not produce better quality clusters when clustering probabilistic face representations that implicitly model uncertainty – these algorithms predict up to 9.6X more clusters than the ground truth for the IJB-A benchmark. We empirically analyze the causes for this unexpected behavior and identify excessive false-positives and false-negatives (when comparing face-pairs) as the main reasons for poor quality clustering. Based on this insight, we propose an uncertainty-aware clustering algorithm, UAC, which explicitly leverages uncertainty information during clustering to decide when a pair of faces are similar or when a predicted cluster should be discarded. UAC considers (a) uncertainty of faces in face-pairs, (b) bins face-pairs into different categories based on an uncertainty threshold, (c) intelligently varies the similarity threshold during clustering to reduce false-negatives and false-positives, and (d) discards predicted clusters that exhibit a high measure of uncertainty. Extensive experimental results on several popular benchmarks and comparisons with state-of-the-art clustering methods show that UAC produces significantly better clusters by leveraging uncertainty in face images – predicted number of clusters is up to 0.18X more of the ground truth for the IJB-A benchmark.","PeriodicalId":226794,"journal":{"name":"2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123428204","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 6

A System for Fusing Color and Near-Infrared Images in Radiance Domain 彩色图像和近红外图像在辐射域的融合系统

2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW) Pub Date : 2021-10-01 DOI: 10.1109/ICCVW54120.2021.00229

K. Ng, Jinglin Shen, C. Ho

引用次数: 0