Related papers: Transformed ROIs for Capturing Visual Transformati…
This paper addresses the task of detecting and recognizing human-object interactions (HOI) in images and videos. We introduce the Graph Parsing Neural Network (GPNN), a framework that incorporates structural knowledge while being…
Video action recognition has made significant strides, but challenges remain in effectively using both spatial and temporal information. While existing methods often focus on either spatial features (e.g., object appearance) or temporal…
Vision-transformers (ViTs) and large-scale convolution-neural-networks (CNNs) have reshaped computer vision through pretrained feature representations that enable strong transfer learning for diverse tasks. However, their efficiency as…
Pedestrian detection has achieved great improvements with the help of Convolutional Neural Networks (CNNs). CNN can learn high-level features from input images, but the insufficient spatial resolution of CNN feature channels (feature maps)…
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…
Anticipating human actions in front of autonomous vehicles is a challenging task. Several papers have recently proposed model architectures to address this problem by combining multiple input features to predict pedestrian crossing actions.…
Action recognition is currently one of the top-challenging research fields in computer vision. Convolutional Neural Networks (CNNs) have significantly boosted its performance but rely on fixed-size spatio-temporal windows of analysis,…
Action recognition in still images has seen major improvement in recent years due to advances in human pose estimation, object recognition and stronger feature representations produced by deep neural networks. However, there are still many…
Reconstructing people, objects, and their interactions in 3D is a long-standing goal for intelligent systems. Often the input is RGB video from a moving camera, making the task ill-posed; depth is ambiguous, humans and objects occlude each…
Detecting human-object interactions (HOIs) is an intricate challenge in the field of computer vision. Existing methods for HOI detection heavily rely on appearance-based features, but these may not fully capture all the essential…
It is a challenging task to learn rich and multi-scale spatiotemporal semantics from high-dimensional videos, due to large local redundancy and complex global dependency between video frames. The recent advances in this research have been…
Video frame interpolation (VFI), which aims to synthesize intermediate frames of a video, has made remarkable progress with development of deep convolutional networks over past years. Existing methods built upon convolutional networks…
Humans typically perceive the establishment of an action in a video through the interaction between an actor and the surrounding environment. An action only starts when the main actor in the video begins to interact with the environment,…
Today's general-purpose deep convolutional neural networks (CNN) for image classification and object detection are trained offline on large static datasets. Some applications, however, will require training in real-time on live video…
Human-object interaction detection (HOID) refers to localizing interactive human-object pairs in images and identifying the interactions. Since there could be an exponential number of object-action combinations, labeled data is limited -…
The explosive growth in video streaming gives rise to challenges on performing video understanding at high accuracy and low computation cost. Conventional 2D CNNs are computationally cheap but cannot capture temporal relationships; 3D CNN…
Video activity recognition by deep neural networks is impressive for many classes. However, it falls short of human performance, especially for challenging to discriminate activities. Humans differentiate these complex activities by…
In this paper, we provide a deep analysis of temporal modeling for action recognition, an important but underexplored problem in the literature. We first propose a new approach to quantify the temporal relationships between frames captured…
Effective processing of video input is essential for the recognition of temporally varying events such as human actions. Motivated by the often distinctive temporal characteristics of actions in either horizontal or vertical direction, we…
Video segmentation encompasses a wide range of categories of problem formulation, e.g., object, scene, actor-action and multimodal video segmentation, for delineating task-specific scene components with pixel-level masks. Recently,…