Related papers: Spot What Matters: Learning Context Using Graph Co…
Given the vast amounts of video available online, and recent breakthroughs in object detection with static images, object detection in video offers a promising new frontier. However, motion blur and compression artifacts cause substantial…
The aim of this paper is threefold. We inform the AI practitioner about the human visual system with an extensive literature review; we propose a novel biologically motivated neural network for image classification; and, finally, we present…
The goal of weakly-supervised video moment retrieval is to localize the video segment most relevant to the given natural language query without access to temporal annotations during training. Prior strongly- and weakly-supervised approaches…
Event perception tasks such as recognizing and localizing actions in streaming videos are essential for scaling to real-world application contexts. We tackle the problem of learning actor-centered representations through the notion of…
Smart devices of everyday use (such as smartphones and wearables) are increasingly integrated with sensors that provide immense amounts of information about a person's daily life such as behavior and context. The automatic and unobtrusive…
Weakly-supervised action localization aims to recognize and localize action instancese in untrimmed videos with only video-level labels. Most existing models rely on multiple instance learning(MIL), where the predictions of unlabeled…
The objective of action quality assessment is to score sports videos. However, most existing works focus only on video dynamic information (i.e., motion information) but ignore the specific postures that an athlete is performing in a video,…
Action parsing in videos with complex scenes is an interesting but challenging task in computer vision. In this paper, we propose a generic 3D convolutional neural network in a multi-task learning manner for effective Deep Action Parsing…
Decoding human activity accurately from wearable sensors can aid in applications related to healthcare and context awareness. The present approaches in this domain use recurrent and/or convolutional models to capture the spatio-temporal…
Person re-identification has achieved great progress with deep convolutional neural networks. However, most previous methods focus on learning individual appearance feature embedding, and it is hard for the models to handle difficult…
We present a new architecture for end-to-end sequence learning of actions in video, we call VideoLSTM. Rather than adapting the video to the peculiarities of established recurrent or convolutional architectures, we adapt the architecture to…
Context plays an important role in visual recognition. Recent studies have shown that visual recognition networks can be fooled by placing objects in inconsistent contexts (e.g., a cow in the ocean). To model the role of contextual…
We propose an approach to learn spatio-temporal features in videos from intermediate visual representations we call "percepts" using Gated-Recurrent-Unit Recurrent Networks (GRUs).Our method relies on percepts that are extracted from all…
We introduce the task of weakly supervised learning for detecting human and object interactions in videos. Our task poses unique challenges as a system does not know what types of human-object interactions are present in a video or the…
Recently, the soft attention mechanism, which was originally proposed in language processing, has been applied in computer vision tasks like image captioning. This paper presents improvements to the soft attention model by combining a…
Weakly-supervised temporal action localization aims to identify and localize the action instances in the untrimmed videos with only video-level action labels. When humans watch videos, we can adapt our abstract-level knowledge about actions…
Increasing the semantic understanding and contextual awareness of machine learning models is important for improving robustness and reducing susceptibility to data shifts. In this work, we leverage contextual awareness for the anomaly…
Enabling computational systems with the ability to localize actions in video-based content has manifold applications. Traditionally, such a problem is approached in a fully-supervised setting where video-clips with complete frame-by-frame…
Existing point-cloud based 3D object detectors use convolution-like operators to process information in a local neighbourhood with fixed-weight kernels and aggregate global context hierarchically. However, non-local neural networks and…
Inspired by the observation that humans are able to process videos efficiently by only paying attention where and when it is needed, we propose an interpretable and easy plug-in spatial-temporal attention mechanism for video action…