Related papers: Depth2Action: Exploring Embedded Depth for Large-S…

Learning-based, single-view depth estimation often generalizes poorly to unseen datasets. While learning-based, two-frame depth estimation solves this problem to some extent by learning to match features across frames, it performs poorly at…

Action recognition is a well-established area of research in computer vision. In this paper, we propose S3Aug, a video data augmenatation for action recognition. Unlike conventional video data augmentation methods that involve cutting and…

This paper addresses the problem of continuous gesture recognition from sequences of depth maps using convolutional neutral networks (ConvNets). The proposed method first segments individual gestures from a depth sequence based on quantity…

In recent years, both online retail and video hosting service are exponentially growing. In this paper, we explore a new cross-domain task, Video2Shop, targeting for matching clothes appeared in videos to the exact same items in online…

Nowadays, the interaction between humans and robots is constantly expanding, requiring more and more human motion recognition applications to operate in real time. However, most works on temporal action detection and recognition perform…

In self-supervised monocular depth estimation, the depth discontinuity and motion objects' artifacts are still challenging problems. Existing self-supervised methods usually utilize a single view to train the depth estimation network.…

Automatically recognizing and localizing wide ranges of human actions has crucial importance for video understanding. Towards this goal, the THUMOS challenge was introduced in 2013 to serve as a benchmark for action recognition. Until then,…

This thesis focuses on video understanding for human action and interaction recognition. We start by identifying the main challenges related to action recognition from videos and review how they have been addressed by current methods. Based…

In this paper, we introduce a challenging new dataset, MLB-YouTube, designed for fine-grained activity detection. The dataset contains two settings: segmented video classification as well as activity detection in continuous videos. We…

Actionness was introduced to quantify the likelihood of containing a generic action instance at a specific location. Accurate and efficient estimation of actionness is important in video analysis and may benefit other relevant tasks such as…

We present a new action recognition deep neural network which adaptively learns the best action velocities in addition to the classification. While deep neural networks have reached maturity for image understanding tasks, we are still…

Identifying unusual driving behaviors exhibited by drivers during driving is essential for understanding driver behavior and the underlying causes of crashes. Previous studies have primarily approached this problem as a classification task,…

For action recognition learning, 2D CNN-based methods are efficient but may yield redundant features due to applying the same 2D convolution kernel to each frame. Recent efforts attempt to capture motion information by establishing…

We propose a function-based temporal pooling method that captures the latent structure of the video sequence data - e.g. how frame-level features evolve over time in a video. We show how the parameters of a function that has been fit to the…

In this paper, we propose a new approach to under-stand actions in egocentric videos that exploits the semantics of object interactions at both frame and temporal levels. At the frame level, we use a region-based approach that takes as…

Recently, there has been a surge of interest in applying deep learning techniques to animal behavior recognition, particularly leveraging pre-trained visual language models, such as CLIP, due to their remarkable generalization capacity…

Sliding window is one direct way to extend a successful recognition system to handle the more challenging detection problem. While action recognition decides only whether or not an action is present in a pre-segmented video sequence, action…

Video motion magnification is a technique to capture and amplify subtle motion in a video that is invisible to the naked eye. The deep learning-based prior work successfully demonstrates the modelling of the motion magnification problem…

Numerous methods for human activity recognition have been proposed in the past two decades. Many of these methods are based on sparse representation, which describes the whole video content by a set of local features. Trajectories, being…

This project investigates the human multi-modal behavior identification algorithm utilizing deep neural networks. According to the characteristics of different modal information, different deep neural networks are used to adapt to different…