Related papers: Part-level Action Parsing via a Pose-guided Coarse…

Action recognition is an important yet challenging task in computer vision. In this paper, we propose a novel deep-based framework for action recognition, which improves the recognition accuracy by: 1) deriving more precise features for…

Video captioning is the task of automatically generating a textual description of the actions in a video. Although previous work (e.g. sequence-to-sequence model) has shown promising results in abstracting a coarse description of a short…

Current methods in training and benchmarking vision models exhibit an over-reliance on passive, curated datasets. Although models trained on these datasets have shown strong performance in a wide variety of tasks such as classification,…

Deep ConvNets have been shown to be effective for the task of human pose estimation from single images. However, several challenging issues arise in the video-based case such as self-occlusion, motion blur, and uncommon poses with few or no…

With advances in data-driven machine learning research, a wide variety of prediction models have been proposed to capture spatio-temporal features for the analysis of video streams. Recognising actions and detecting action transitions…

Encouraged by the success of Convolutional Neural Networks (CNNs) in image classification, recently much effort is spent on applying CNNs to video based action recognition problems. One challenge is that video contains a varying number of…

Video predictive understanding encompasses a wide range of efforts that are concerned with the anticipation of the unobserved future from the current as well as historical video observations. Action prediction is a major sub-area of video…

Most state-of-the-art methods for action recognition rely only on 2D spatial features encoding appearance, motion or pose. However, 2D data lacks the depth information, which is crucial for recognizing fine-grained actions. In this paper,…

Action recognition models have achieved promising results in understanding instructional videos. However, they often rely on dominant, dataset-specific action sequences rather than true video comprehension, a problem that we define as…

Large vision-language models (VLMs) have advanced multimodal tasks such as video question answering (QA). However, VLMs face the challenge of selecting frames effectively and efficiently, as standard uniform sampling is expensive and…

Human action recognition in video is an active yet challenging research topic due to high variation and complexity of data. In this paper, a novel video based action recognition framework utilizing complementary cues is proposed to handle…

Standard methods for video recognition use large CNNs designed to capture spatio-temporal data. However, training these models requires a large amount of labeled training data, containing a wide variety of actions, scenes, settings and…

Inspired by the fact that human eyes continue to develop tracking ability in early and middle childhood, we propose to use tracking as a proxy task for a computer vision system to learn the visual representations. Modelled on the Catch game…

Action segmentation of behavioral videos is the process of labeling each frame as belonging to one or more discrete classes, and is a crucial component of many studies that investigate animal behavior. A wide range of algorithms exist to…

Video-based human pose estimation models aim to address scenarios that cannot be effectively solved by static image models such as motion blur, out-of-focus and occlusion. Most existing approaches consist of two stages: detecting human…

Weakly supervised temporal action localization (WTAL) aims to detect action instances in untrimmed videos using only video-level annotations. Since many existing works optimize WTAL models based on action classification labels, they…

Motion plays a crucial role in understanding videos and most state-of-the-art neural models for video classification incorporate motion information typically using optical flows extracted by a separate off-the-shelf method. As the…

Active learning is considered a viable solution to alleviate the contradiction between the high dependency of deep learning-based segmentation methods on annotated data and the expensive pixel-level annotation cost of medical images.…

In recent years, video semantic segmentation has made great progress with advanced deep neural networks. However, there still exist two main challenges \ie, information inconsistency and computation cost. To deal with the two difficulties,…

Recovering structure and motion parameters given a image pair or a sequence of images is a well studied problem in computer vision. This is often achieved by employing Structure from Motion (SfM) or Simultaneous Localization and Mapping…