3D object detection has become indispensable in the field of autonomous driving. To date, gratifying breakthroughs have been recorded in 3D object detection research, attributed to deep learning. However, deep learning algorithms are data-driven and require large amounts of annotated point cloud data for training and evaluation. Unlike 2D images, annotating point cloud data is difficult due to the limitations of sparsity, irregularity, and low resolution, which requires more manual work, and the annotation efficiency is much lower than annotating 2D images. Therefore, we propose an annotation algorithm for point cloud data, which is pre-annotation and camera-LiDAR late fusion algorithm to annotate easily and accurately.
{"title":"PALF: Pre-Annotation and Camera-LiDAR Late Fusion for the Easy Annotation of Point Clouds","authors":"Yucheng Zhang, Masaki Fukuda, Yasunori Ishii, Kyoko Ohshima, Takayoshi Yamashita","doi":"10.23919/MVA57639.2023.10216156","DOIUrl":"https://doi.org/10.23919/MVA57639.2023.10216156","url":null,"abstract":"3D object detection has become indispensable in the field of autonomous driving. To date, gratifying breakthroughs have been recorded in 3D object detection research, attributed to deep learning. However, deep learning algorithms are data-driven and require large amounts of annotated point cloud data for training and evaluation. Unlike 2D images, annotating point cloud data is difficult due to the limitations of sparsity, irregularity, and low resolution, which requires more manual work, and the annotation efficiency is much lower than annotating 2D images. Therefore, we propose an annotation algorithm for point cloud data, which is pre-annotation and camera-LiDAR late fusion algorithm to annotate easily and accurately.","PeriodicalId":338734,"journal":{"name":"2023 18th International Conference on Machine Vision and Applications (MVA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131890785","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}
Pub Date : 2022-09-26DOI: 10.23919/MVA57639.2023.10215754
Ahmed Sabir
This paper focuses on enhancing the captions generated by image captioning systems. We propose an approach for improving caption generation systems by choosing the most closely related output to the image rather than the most likely output produced by the model. Our model revises the language generation output beam search from a visual context perspective. We employ a visual semantic measure in a word and sentence level manner to match the proper caption to the related information in the image. This approach can be applied to any caption system as a post-processing method.
{"title":"Word to Sentence Visual Semantic Similarity for Caption Generation: Lessons Learned","authors":"Ahmed Sabir","doi":"10.23919/MVA57639.2023.10215754","DOIUrl":"https://doi.org/10.23919/MVA57639.2023.10215754","url":null,"abstract":"This paper focuses on enhancing the captions generated by image captioning systems. We propose an approach for improving caption generation systems by choosing the most closely related output to the image rather than the most likely output produced by the model. Our model revises the language generation output beam search from a visual context perspective. We employ a visual semantic measure in a word and sentence level manner to match the proper caption to the related information in the image. This approach can be applied to any caption system as a post-processing method.","PeriodicalId":338734,"journal":{"name":"2023 18th International Conference on Machine Vision and Applications (MVA)","volume":"130 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115249652","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}
Pub Date : 2021-12-16DOI: 10.23919/MVA57639.2023.10215534
Junwen Chen, Keiji Yanai
Human-object interaction (HOI) detection as a downstream of object detection task requires localizing pairs of humans and objects and recognizing the interaction between them. Recent one-stage approaches focus on detecting possible interaction points or filtering human-object pairs, ignoring the variability in the location and size of different objects at spatial scales. In this paper, we propose a transformer-based method, QAHOI (Query-Based Anchors for Human-Object Interaction detection), which leverages a multi-scale architecture to extract features from different spatial scales and uses query-based anchors to predict all the elements of an HOI instance. We further investigate that a powerful backbone significantly increases accuracy for QAHOI, and QAHOI with a transformer-based backbone outperforms recent state-of-the-art methods by large margins on the HICO-DET benchmark.
{"title":"QAHOI: Query-Based Anchors for Human-Object Interaction Detection","authors":"Junwen Chen, Keiji Yanai","doi":"10.23919/MVA57639.2023.10215534","DOIUrl":"https://doi.org/10.23919/MVA57639.2023.10215534","url":null,"abstract":"Human-object interaction (HOI) detection as a downstream of object detection task requires localizing pairs of humans and objects and recognizing the interaction between them. Recent one-stage approaches focus on detecting possible interaction points or filtering human-object pairs, ignoring the variability in the location and size of different objects at spatial scales. In this paper, we propose a transformer-based method, QAHOI (Query-Based Anchors for Human-Object Interaction detection), which leverages a multi-scale architecture to extract features from different spatial scales and uses query-based anchors to predict all the elements of an HOI instance. We further investigate that a powerful backbone significantly increases accuracy for QAHOI, and QAHOI with a transformer-based backbone outperforms recent state-of-the-art methods by large margins on the HICO-DET benchmark.","PeriodicalId":338734,"journal":{"name":"2023 18th International Conference on Machine Vision and Applications (MVA)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125564531","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}
Pub Date : 2021-12-07DOI: 10.23919/MVA57639.2023.10216260
Srijan Das, M. Ryoo
In this paper, we address the challenge of obtaining large-scale unlabelled video datasets for contrastive representation learning in real-world applications. We present a novel video augmentation technique for self-supervised learning, called Cross-Modal Manifold Cutmix (CMMC), which generates augmented samples by combining different modalities in videos. By embedding a video tesseract into another across two modalities in the feature space, our method enhances the quality of learned video representations. We perform extensive experiments on two small-scale video datasets, UCF101 and HMDB51, for action recognition and video retrieval tasks. Our approach is also shown to be effective on the NTU dataset with limited domain knowledge. Our CMMC achieves comparable performance to other self-supervised methods while using less training data for both downstream tasks.
{"title":"Cross-modal Manifold Cutmix for Self-supervised Video Representation Learning","authors":"Srijan Das, M. Ryoo","doi":"10.23919/MVA57639.2023.10216260","DOIUrl":"https://doi.org/10.23919/MVA57639.2023.10216260","url":null,"abstract":"In this paper, we address the challenge of obtaining large-scale unlabelled video datasets for contrastive representation learning in real-world applications. We present a novel video augmentation technique for self-supervised learning, called Cross-Modal Manifold Cutmix (CMMC), which generates augmented samples by combining different modalities in videos. By embedding a video tesseract into another across two modalities in the feature space, our method enhances the quality of learned video representations. We perform extensive experiments on two small-scale video datasets, UCF101 and HMDB51, for action recognition and video retrieval tasks. Our approach is also shown to be effective on the NTU dataset with limited domain knowledge. Our CMMC achieves comparable performance to other self-supervised methods while using less training data for both downstream tasks.","PeriodicalId":338734,"journal":{"name":"2023 18th International Conference on Machine Vision and Applications (MVA)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126932278","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：