Related papers: Object-ABN: Learning to Generate Sharp Attention M…

Current state-of-the-art video models process a video clip as a long sequence of spatio-temporal tokens. However, they do not explicitly model objects, their interactions across the video, and instead process all the tokens in the video. In…

As the request for deep learning solutions increases, the need for explainability is even more fundamental. In this setting, particular attention has been given to visualization techniques, that try to attribute the right relevance to each…

Existing action recognition methods typically sample a few frames to represent each video to avoid the enormous computation, which often limits the recognition performance. To tackle this problem, we propose Ample and Focal Network (AFNet),…

The prevalence of employing attention mechanisms has brought along concerns on the interpretability of attention distributions. Although it provides insights about how a model is operating, utilizing attention as the explanation of model…

Object detection is one of the most important and fundamental aspects of computer vision tasks, which has been broadly utilized in pose estimation, object tracking and instance segmentation models. To obtain training data for object…

This paper studies the object transfiguration problem in wild images. The generative network in classical GANs for object transfiguration often undertakes a dual responsibility: to detect the objects of interests and to convert the object…

State-of-the-art methods in image-to-image translation are capable of learning a mapping from a source domain to a target domain with unpaired image data. Though the existing methods have achieved promising results, they still produce…

Inspired by recent advances in neural machine translation, that jointly align and translate using encoder-decoder networks equipped with attention, we propose an attentionbased LSTM model for human activity recognition. Our model jointly…

Conventional salient object detection models cannot differentiate the importance of different salient objects. Recently, two works have been proposed to detect saliency ranking by assigning different degrees of saliency to different…

This paper presents a novel keypoints-based attention mechanism for visual recognition in still images. Deep Convolutional Neural Networks (CNNs) for recognizing images with distinctive classes have shown great success, but their…

The Convolutional Neural Network (CNN) is a widely used deep learning architecture for computer vision. However, its black box nature makes it difficult to interpret the behavior of the model. To mitigate this issue, AI practitioners have…

We present a novel facial expression recognition network, called Distract your Attention Network (DAN). Our method is based on two key observations. Firstly, multiple classes share inherently similar underlying facial appearance, and their…

We propose the gradient-weighted Object Detector Activation Maps (ODAM), a visualized explanation technique for interpreting the predictions of object detectors. Utilizing the gradients of detector targets flowing into the intermediate…

Fine-grained visual recognition typically depends on modeling subtle difference from object parts. However, these parts often exhibit dramatic visual variations such as occlusions, viewpoints, and spatial transformations, making it hard to…

Event cameras, which capture brightness changes with high temporal resolution, inherently generate a significant amount of redundant and noisy data beyond essential object structures. The primary challenge in event-based object recognition…

The attention mechanism has been proven effective on various visual tasks in recent years. In the semantic segmentation task, the attention mechanism is applied in various methods, including the case of both Convolution Neural Networks…

Reflection on one's thought process and making corrections to it if there exists dissatisfaction in its performance is, perhaps, one of the essential traits of intelligence. However, such high-level abstract concepts mandatory for…

Road safety mapping using satellite images is a cost-effective but a challenging problem for smart city planning. The scarcity of labeled data, misalignment and ambiguity makes it hard for supervised deep networks to learn efficient…

Visual attention has proven to be effective in improving the performance of person re-identification. Most existing methods apply visual attention heuristically by learning an additional attention map to re-weight the feature maps for…

This work proposes a novel attentive graph neural network (AGNN) for zero-shot video object segmentation (ZVOS). The suggested AGNN recasts this task as a process of iterative information fusion over video graphs. Specifically, AGNN builds…