Related papers: Memory Warps for Learning Long-Term Online Video R…
A number of computer vision tasks exploit a succinct representation of the visual content in the form of sets of local features. Given an input image, feature extraction algorithms identify a set of keypoints and assign to each of them a…
While single image shadow detection has been improving rapidly in recent years, video shadow detection remains a challenging task due to data scarcity and the difficulty in modelling temporal consistency. The current video shadow detection…
Self-supervised learning of image representations by predicting future frames is a promising direction but still remains a challenge. This is because of the under-determined nature of frame prediction; multiple potential futures can arise…
Video prediction is commonly referred to as forecasting future frames of a video sequence provided several past frames thereof. It remains a challenging domain as visual scenes evolve according to complex underlying dynamics, such as the…
In 3D human action recognition, limited supervised data makes it challenging to fully tap into the modeling potential of powerful networks such as transformers. As a result, researchers have been actively investigating effective…
Real-time visibility determination in expansive or dynamically changing environments has long posed a significant challenge in computer graphics. Existing techniques are computationally expensive and often applied as a precomputation step…
A dynamic scene has two types of elements: those that move fluidly and can be predicted from previous frames, and those which are disoccluded (exposed) and cannot be extrapolated. Prior approaches to video prediction typically learn either…
Recent advances in visual representation learning allowed to build an abundance of powerful off-the-shelf features that are ready-to-use for numerous downstream tasks. This work aims to assess how well these features preserve information…
Online continual learning for image classification is crucial for models to adapt to new data while retaining knowledge of previously learned tasks. This capability is essential to address real-world challenges involving dynamic…
To exploit high temporal correlations in video frames of the same scene, the current frame is predicted from the already-encoded reference frames using block-based motion estimation and compensation techniques. While this approach can…
In this dissertation, I present my work towards exploring temporal information for better video understanding. Specifically, I have worked on two problems: action recognition and semantic segmentation. For action recognition, I have…
Video object detection is more challenging compared to image object detection. Previous works proved that applying object detector frame by frame is not only slow but also inaccurate. Visual clues get weakened by defocus and motion blur,…
We address temporal action localization in untrimmed long videos. This is important because videos in real applications are usually unconstrained and contain multiple action instances plus video content of background scenes or other…
Deep neural networks based methods have been proved to achieve outstanding performance on object detection and classification tasks. Despite significant performance improvement, due to the deep structures, they still require prohibitive…
Semantic segmentation of LiDAR point clouds has been widely studied in recent years, with most existing methods focusing on tackling this task using a single scan of the environment. However, leveraging the temporal stream of observations…
In this paper we propose an unsupervised feature extraction method to capture temporal information on monocular videos, where we detect and encode subject of interest in each frame and leverage contrastive self-supervised (CSS) learning to…
Point tracking aims to identify the same physical point across video frames and serves as a geometry-aware representation of motion. This representation supports a wide range of applications, from robotics to augmented reality, by enabling…
We present a large-scale study on unsupervised spatiotemporal representation learning from videos. With a unified perspective on four recent image-based frameworks, we study a simple objective that can easily generalize all these methods to…
We introduce a weakly supervised method for representation learning based on aligning temporal sequences (e.g., videos) of the same process (e.g., human action). The main idea is to use the global temporal ordering of latent correspondences…
Current state-of-the-art models for video action recognition are mostly based on expensive 3D ConvNets. This results in a need for large GPU clusters to train and evaluate such architectures. To address this problem, we present a…