Weakly-supervised temporal action localization (WTAL) in untrimmed videos has emerged as a practical but challenging task since only video-level labels are available. Existing approaches typically leverage off-the-shelf segment-level features, which suffer from spatial incompleteness and temporal incoherence, thus limiting their performance. In this paper, we tackle this problem from a new perspective by enhancing segment-level representations with a simple yet effective graph convolutional network, namely action complement graph network (ACGNet). It facilitates the current video segment to perceive spatial-temporal dependencies from others that potentially convey complementary clues, implicitly mitigating the negative effects caused by the two issues above. By this means, the segment-level features are more discriminative and robust to spatial-temporal variations, contributing to higher localization accuracies. More importantly, the proposed ACGNet works as a universal module that can be flexibly plugged into different WTAL frameworks, while maintaining the end-to-end training fashion. Extensive experiments are conducted on the THUMOS'14 and ActivityNet1.2 benchmarks, where the state-of-the-art results clearly demonstrate the superiority of the proposed approach.

In this work, we propose a two-stage framework to efficiently and effectively detect actions on-the-fly. An action location network (ALN) is developed in the first stage to judge whether the current frame is action-related, while the second stage involves an action classification network (ACN) to further identify the action category. In this way, irrelevant negative frames are quickly discarded and actions are detected as early as they occur. Moreover, we highlight human areas at both the stages by respectively incorporating a human detector and a human mask layer. As a result, more accurate spatial-temporal windows of actions are detected, based on which more robust features are extracted for classification. Experimental results on two popular benchmarks demonstrate the superior performance of the proposed approach.

With the development of remote sensing satellite technology, the resolution of remote sensing images is constantly improved, but there are difficulties in obtaining labeled SAR image datasets for target detection and recognition. To address the problem that only limited SAR image target detection and recognition data are available, a novel data augmentation method based on convolutional neural network is proposed. Firstly, the Synthetic Aperture Radar (SAR) image target detection and recognition dataset SAR_OD was produced based on the synthesis of military targets and background images in MSTAR dataset. But considering the fact that the number of targets in each image in SAR_OD is still not enough for training a target detection model with good performance, we augmented SAR_OD and then we obtained SAR_OD+ dataset. It is proved that the model trained on SAR_OD+ dataset is significantly improved in the evaluation index by the data augmentation method proposed in this paper, especially in the experiments using only 50% of the training data. Therefore, the proposed data augmentation method can be used to improve the performance of SAR image target detection and recognition model in the case of limited labeled data.

Convolutional neural networks have gained a remarkable success in computer vision. However, most popular network architectures are hand-crafted and usually require expertise and elaborate design. In this paper, we provide a block-wise network generation pipeline called BlockQNN which automatically builds high-performance networks using the Q-Learning paradigm with epsilon-greedy exploration strategy. The optimal network block is constructed by the learning agent which is trained to choose component layers sequentially. We stack the block to construct the whole auto-generated network. To accelerate the generation process, we also propose a distributed asynchronous framework and an early stop strategy. The block-wise generation brings unique advantages: (1) it yields state-of-the-art results in comparison to the hand-crafted networks on image classification, particularly, the best network generated by BlockQNN achieves 2.35 percent top-1 error rate on CIFAR-10. (2) it offers tremendous reduction of the search space in designing networks, spending only 3 days with 32 GPUs. A faster version can yield a comparable result with only 1 GPU in 20 hours. (3) it has strong generalizability in that the network built on CIFAR also performs well on the larger-scale dataset. The best network achieves very competitive accuracy of 82.0 percent top-1 and 96.0 percent top-5 on ImageNet.

Many image processing tasks can be formulated as translating images between two image domains, such as colorization, super-resolution, and conditional image synthesis. In most of these tasks, an input image may correspond to multiple outputs. However, current existing approaches only show minor stochasticity of the outputs. In this paper, we present a novel approach to synthesize diverse realistic images corresponding to a semantic layout. We introduce a diversity loss objective, which maximizes the distance between synthesized image pairs and relates the input noise to the semantic segments in the synthesized images. Thus, our approach can not only produce multiple diverse images but also allow users to manipulate the output images by adjusting the noise manually. Experimental results show that images synthesized by our approach are diverse than that of the current existing works and equipping our diversity loss does not degrade the reality of the base networks. Moreover, our approach can be applied to unpaired datasets.