Gen Li  

Humans excel at acquiring knowledge through observation. For example, we can learn to use new tools by watching demonstrations. This skill is fundamental for intelligent systems to interact with the world. A key step to acquire this skill is to identify what part of the object affords each action, which is called affordance grounding. In this paper, we address this problem and propose a framework called LOCATE that can identify matching object parts across images, to transfer knowledge from images where an object is being used (exocentric images used for learning), to images where the object is inactive (egocentric ones used to test). To this end, we first find interaction areas and extract their feature embeddings. Then we learn to aggregate the embeddings into compact prototypes (human, object part, and background), and select the one representing the object part. Finally, we use the selected prototype to guide affordance grounding. We do this in a weakly supervised manner, learning only from image-level affordance and object labels. Extensive experiments demonstrate that our approach outperforms state-of-the-art methods by a large margin on both seen and unseen objects.

Prototype learning is extensively used for few-shot segmentation. Typically, a single prototype is obtained from the support feature by averaging the global object information. However, using one prototype to represent all the information may lead to ambiguities. In this paper, we propose two novel modules, named superpixel-guided clustering (SGC) and guided prototype allocation (GPA), for multiple prototype extraction and allocation. Specifically, SGC is a parameter-free and training-free approach, which extracts more representative prototypes by aggregating similar feature vectors, while GPA is able to select matched prototypes to provide more accurate guidance. By integrating the SGC and GPA together, we propose the Adaptive Superpixelguided Network (ASGNet), which is a lightweight model and adapts to object scale and shape variation. In addition, our network can easily generalize to k-shot segmentation with substantial improvement and no additional computational cost. In particular, our evaluations on COCO demonstrate that ASGNet surpasses the state-of-the-art method by 5% in 5-shot segmentation.

As a pixel-level prediction task, semantic segmentation needs large computational cost with enormous parameters to obtain high performance. Recently, due to the increasing demand for autonomous systems and robots, it is significant to make a tradeoff between accuracy and inference speed. In this paper, we propose a novel Depth-wise Asymmetric Bottleneck (DAB) module to address this dilemma, which efficiently adopts depth-wise asymmetric convolution and dilated convolution to build a bottleneck structure. Based on the DAB module, we design a Depth-wise Asymmetric Bottleneck Network (DABNet) especially for real-time semantic segmentation, which creates sufficient receptive field and densely utilizes the contextual information. Experiments on Cityscapes and CamVid datasets demonstrate that the proposed DABNet achieves a balance between speed and precision. Specifically, without any pretrained model and post-processing, it achieves 70.1% Mean IoU on the Cityscapes test dataset with only 0.76 million parameters and a speed of 104 FPS on a single GTX 1080Ti card.

From a series of observations, we have inferred that human actions in videos are defined by a set of significant frames. In this paper, we propose a weakly-supervised temporal attention 3D network for human action recognition, called as TA3DNet, to accelerate 3D convolutional neural networks (3D CNNs) by temporally assigning different importance to each frame. First, we obtain short-term frames with long-term connection by regularly or randomly skipping frames to avoid temporal redundancy, and apply 3D convolutional layers to extract features for action recognition. Then, we apply a temporal attention module to assign different weights to each frame. We train the temporal attention module in a weakly-supervised manner that updates weights based on only class labels without event information and extra labels. Thus, TA3DNet reduces the number of input frames and constructs a lightweight network for action recognition. Experimental results demonstrate that TA3DNet achieves high performance on two challenging datasets (UCF101 and HMDB51) and outperforms state-of-the-art methods for action recognition.

Face super-resolution (SR) has become an indispensable function in security solutions such as video surveillance and identification system, but the distortion in facial components is a great challenge in it. Most state-of-the-art methods have utilized facial priors with deep neural networks. These methods require extra labels, longer training time, and larger computation memory. In this paper, we propose a novel Edge and Identity Preserving Network for Face SR Network, named as EIPNet, to minimize the distortion by utilizing a lightweight edge block and identity information. We present an edge block to extract perceptual edge information, and concatenate it to the original feature maps in multiple scales. This structure progressively provides edge information in reconstruction to aggregate local and global structural information. Moreover, we define an identity loss function to preserve identification of SR images. The identity loss function compares feature distributions between SR images and their ground truth to recover identities in SR images. In addition, we provide a luminance-chrominance error (LCE) to separately infer brightness and color information in SR images. The LCE method not only reduces the dependency of color information by dividing brightness and color components but also enables our network to reflect differences between SR images and their ground truth in two color spaces of RGB and YUV. The proposed method facilitates the proposed SR network to elaborately restore facial components and generate high quality 8× scaled SR images with a lightweight network structure. Furthermore, our network is able to reconstruct an 128×128 SR image with 215 fps on a GTX 1080Ti GPU. Extensive experiments demonstrate that our network qualitatively and quantitatively outperforms state-of-the-art methods on two challenging datasets: CelebA and VGGFace2.