Related papers: Attentional Pooling for Action Recognition

Image segmentation is a historic and significant computer vision task. With the help of deep learning techniques, image semantic segmentation has made great progresses. Over recent years, based on guidance of attention mechanism compared…

Recent advances in deep neural networks have been developed via architecture search for stronger representational power. In this work, we focus on the effect of attention in general deep neural networks. We propose a simple and effective…

In this paper, we introduce a novel hierarchical aggregation design that captures different levels of temporal granularity in action recognition. Our design principle is coarse-to-fine and achieved using a tree-structured network; as we…

In this paper we propose to augment a modern neural-network architecture with an attention model inspired by human perception. Specifically, we adversarially train and analyze a neural model incorporating a human inspired, visual attention…

Representation learning produces models in different domains, such as store purchases, client transactions, and general people's behavior. However, such models for event sequences usually process each sequence in isolation, ignoring context…

Vehicle Re-identification is a challenging task due to intra-class variability and inter-class similarity across non-overlapping cameras. To tackle these problems, recently proposed methods require additional annotation to extract more…

Despite the notable progress made in action recognition tasks, not much work has been done in action recognition specifically for human-robot interaction. In this paper, we deeply explore the characteristics of the action recognition task…

Visual attention has shown usefulness in image captioning, with the goal of enabling a caption model to selectively focus on regions of interest. Existing models typically rely on top-down language information and learn attention implicitly…

Deep learning models for video-based action recognition usually generate features for short clips (consisting of a few frames); such clip-level features are aggregated to video-level representations by computing statistics on these…

Feature fusion, the combination of features from different layers or branches, is an omnipresent part of modern network architectures. It is often implemented via simple operations, such as summation or concatenation, but this might not be…

Object-based attention is a key component of the visual system, relevant for perception, learning, and memory. Neurons tuned to features of attended objects tend to be more active than those associated with non-attended objects. There is a…

User interests are usually dynamic in the real world, which poses both theoretical and practical challenges for learning accurate preferences from rich behavior data. Among existing user behavior modeling solutions, attention networks are…

Retrieval augmented models are becoming increasingly popular for computer vision tasks after their recent success in NLP problems. The goal is to enhance the recognition capabilities of the model by retrieving similar examples for the…

Self-attention networks have shown remarkable progress in computer vision tasks such as image classification. The main benefit of the self-attention mechanism is the ability to capture long-range feature interactions in attention-maps.…

The interactions between human and objects are important for recognizing object-centric actions. Existing methods usually adopt a two-stage pipeline, where object proposals are first detected using a pretrained detector, and then are fed to…

Modern neural networks are powerful predictive models. However, when it comes to recognizing that they may be wrong about their predictions, they perform poorly. For example, for one of the most common activation functions, the ReLU and its…

Deep robot vision models are widely used for recognizing objects from camera images, but shows poor performance when detecting objects at untrained positions. Although such problem can be alleviated by training with large datasets, the…

Visual attention is a mechanism closely intertwined with vision and memory. Top-down information influences visual processing through attention. We designed a neural network model inspired by aspects of human visual attention. This model…

Deep neural networks have recently achieved competitive accuracy for human activity recognition. However, there is room for improvement, especially in modeling long-term temporal importance and determining the activity relevance of…

Multi-task learning has been widely adopted in many computer vision tasks to improve overall computation efficiency or boost the performance of individual tasks, under the assumption that those tasks are correlated and complementary to each…