Related papers: DEVIAS: Learning Disentangled Video Representation…
In this work, we present a novel approach to multi-view action recognition where we guide learned action representations to be separated from view-relevant information in a video. When trying to classify action instances captured from…
A unified video and action model holds significant promise for robotics, where videos provide rich scene information for action prediction, and actions provide dynamics information for video prediction. However, effectively combining video…
Deep learning models have achieved excellent recognition results on large-scale video benchmarks. However, they perform poorly when applied to videos with rare scenes or objects, primarily due to the bias of existing video datasets. We…
Video representation learning has recently attracted attention in computer vision due to its applications for activity and scene forecasting or vision-based planning and control. Video prediction models often learn a latent representation…
Missing data poses significant challenges while learning representations of video sequences. We present Disentangled Imputed Video autoEncoder (DIVE), a deep generative model that imputes and predicts future video frames in the presence of…
Effective explanations of video action recognition models should disentangle how movements unfold over time from the surrounding spatial context. However, existing methods based on saliency produce entangled explanations, making it unclear…
Action recognition and anticipation are key to the success of many computer vision applications. Existing methods can roughly be grouped into those that extract global, context-aware representations of the entire image or sequence, and…
One significant factor we expect the video representation learning to capture, especially in contrast with the image representation learning, is the object motion. However, we found that in the current mainstream video datasets, some action…
Trajectory prediction is a critical component of autonomous driving, essential for ensuring both safety and efficiency on the road. However, traditional approaches often struggle with the scarcity of labeled data and exhibit suboptimal…
We present a learning algorithm for human activity recognition in videos. Our approach is designed for UAV videos, which are mainly acquired from obliquely placed dynamic cameras that contain a human actor along with background motion.…
The objective of this paper is self-supervised learning of spatio-temporal embeddings from video, suitable for human action recognition. We make three contributions: First, we introduce the Dense Predictive Coding (DPC) framework for…
This paper introduces an unsupervised framework to extract semantically rich features for video representation. Inspired by how the human visual system groups objects based on motion cues, we propose a deep convolutional neural network that…
Human activities often occur in specific scene contexts, e.g., playing basketball on a basketball court. Training a model using existing video datasets thus inevitably captures and leverages such bias (instead of using the actual…
Action recognition is a fundamental task in video understanding. Existing methods typically extract unified features to process all actions in one video, which makes it challenging to model the interactions between different objects in…
Deep learning models have a risk of utilizing spurious clues to make predictions, such as recognizing actions based on the background scene. This issue can severely degrade the open-set action recognition performance when the testing…
Video Instance Segmentation (VIS) jointly tackles multi-object detection, tracking, and segmentation in video sequences. In the past, VIS methods mirrored the fragmentation of these subtasks in their architectural design, hence missing out…
Deep neural networks are susceptible to learn biased models with entangled feature representations, which may lead to subpar performances on various downstream tasks. This is particularly true for under-represented classes, where a lack of…
Detecting anomalies in human-related videos is crucial for surveillance applications. Current methods primarily include appearance-based and action-based techniques. Appearance-based methods rely on low-level visual features such as color,…
Existing zero-shot skeleton-based action recognition methods utilize projection networks to learn a shared latent space of skeleton features and semantic embeddings. The inherent imbalance in action recognition datasets, characterized by…
Disentangled representation learning has seen a surge in interest over recent times, generally focusing on new models which optimise one of many disparate disentanglement metrics. Symmetry Based Disentangled Representation learning…