UntrimmedNets for Weakly Supervised Action Recognition and Detection
Limin Wang,Yuanjun Xiong,Dahua Lin,Luc Van Gool +3 more
- pp 6402-6411
TLDR
This paper presents a new weakly supervised architecture, called UntrimmedNet, which is able to directly learn action recognition models from untrimmed videos without the requirement of temporal annotations of action instances.Abstract:
Current action recognition methods heavily rely on trimmed videos for model training. However, it is expensive and time-consuming to acquire a large-scale trimmed video dataset. This paper presents a new weakly supervised architecture, called UntrimmedNet, which is able to directly learn action recognition models from untrimmed videos without the requirement of temporal annotations of action instances. Our UntrimmedNet couples two important components, the classification module and the selection module, to learn the action models and reason about the temporal duration of action instances, respectively. These two components are implemented with feed-forward networks, and UntrimmedNet is therefore an end-to-end trainable architecture. We exploit the learned models for action recognition (WSR) and detection (WSD) on the untrimmed video datasets of THUMOS14 and ActivityNet. Although our UntrimmedNet only employs weak supervision, our method achieves performance superior or comparable to that of those strongly supervised approaches on these two datasets.read more
Citations
More filters
Proceedings ArticleDOI
Mr.CAN: Class-Aware Network with Multi-Relations for Temporal Action Detection
TL;DR: Wang et al. as discussed by the authors proposed a class-aware network with multi-relations (MrCAN) to detect temporal and semantic relations between different segments, which achieved state-of-the-art performance.
Journal ArticleDOI
Open-Vocabulary Temporal Action Detection with Off-the-Shelf Image-Text Features
Vivek Rathod,Bryan Seybold,Sudheendra Vijayanarasimhan,Austin Myers,Xiuye Gu,Vighnesh Birodkar,David A. Ross +6 more
TL;DR: In this article , an open-vocabulary temporal action detection method was proposed using image-text co-embeddings, which can be further improved by ensembling the imagetext features with features encoding local motion, like optical flow based features or other modalities, like audio.
Learning Disentangled Classification and Localization Representations for Temporal Action Localization
TL;DR: This paper disentangled the shared representation of Temporal Action Localization into classification and localization representations, and evaluates the proposed method on two popular benchmarks for TAL, which outperforms all state-of-the-art methods.
Book ChapterDOI
Two-Stage Recognition Algorithm for Untrimmed Converter Steelmaking Flame Video.
Yi Chen,Jiyuan Liu,Huilin Xiong +2 more
TL;DR: Li et al. as mentioned in this paper proposed a two-stage recognition algorithm to identify converter status using furnace flame video, in which a 2D feature extractor based on the shift module was designed to capture temporal information in real time.
Proceedings ArticleDOI
BACNet: Boundary-Anchor Complementary Network for Temporal Action Detection
TL;DR: In this paper , two supplementary modules are designed to enhance snippet-level boundary segmentation and anchor-level action evaluation, which achieves the state-of-the-art performance on both THUMOS-14 and ActivityNet-1.3 datasets.
References
More filters
Proceedings Article
ImageNet Classification with Deep Convolutional Neural Networks
TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.
Proceedings ArticleDOI
ImageNet: A large-scale hierarchical image database
TL;DR: A new database called “ImageNet” is introduced, a large-scale ontology of images built upon the backbone of the WordNet structure, much larger in scale and diversity and much more accurate than the current image datasets.
Journal ArticleDOI
Gradient-based learning applied to document recognition
Yann LeCun,Léon Bottou,Léon Bottou,Yoshua Bengio,Yoshua Bengio,Yoshua Bengio,Patrick Haffner +6 more
TL;DR: In this article, a graph transformer network (GTN) is proposed for handwritten character recognition, which can be used to synthesize a complex decision surface that can classify high-dimensional patterns, such as handwritten characters.
Proceedings Article
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Sergey Ioffe,Christian Szegedy +1 more
TL;DR: Applied to a state-of-the-art image classification model, Batch Normalization achieves the same accuracy with 14 times fewer training steps, and beats the original model by a significant margin.
Journal ArticleDOI
ImageNet Large Scale Visual Recognition Challenge
Olga Russakovsky,Jia Deng,Hao Su,Jonathan Krause,Sanjeev Satheesh,Sean Ma,Zhiheng Huang,Andrej Karpathy,Aditya Khosla,Michael S. Bernstein,Alexander C. Berg,Li Fei-Fei +11 more
TL;DR: The ImageNet Large Scale Visual Recognition Challenge (ILSVRC) as mentioned in this paper is a benchmark in object category classification and detection on hundreds of object categories and millions of images, which has been run annually from 2010 to present, attracting participation from more than fifty institutions.
Related Papers (5)
Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset
Joao Carreira,Andrew Zisserman +1 more