Related papers: TraMNet - Transition Matrix Network for Efficient …

Temporal action localization is an important yet challenging task in video understanding. Typically, such a task aims at inferring both the action category and localization of the start and end frame for each action instance in a long,…

Data association is a crucial component for any multiple object tracking (MOT) method that follows the tracking-by-detection paradigm. To generate complete trajectories such methods employ a data association process to establish assignments…

Convolutional neural networks have become the main tools for processing two-dimensional data. They work well for images, yet convolutions have a limited receptive field that prevents its applications to more complex 2D tasks. We propose a…

Most existing deep neural networks are static, which means they can only do inference at a fixed complexity. But the resource budget can vary substantially across different devices. Even on a single device, the affordable budget can change…

This technical report presents our first place winning solution for temporal action detection task in CVPR-2022 AcitivityNet Challenge. The task aims to localize temporal boundaries of action instances with specific classes in long…

Although various image-based domain adaptation (DA) techniques have been proposed in recent years, domain shift in videos is still not well-explored. Most previous works only evaluate performance on small-scale datasets which are saturated.…

Robust object tracking requires knowledge of tracked objects' appearance, motion and their evolution over time. Although motion provides distinctive and complementary information especially for fast moving objects, most of the recent…

Object detection and object tracking are usually treated as two separate processes. Significant progress has been made for object detection in 2D images using deep learning networks. The usual tracking-by-detection pipeline for object…

This work introduces a new training and compression pipeline to build Nested Sparse ConvNets, a class of dynamic Convolutional Neural Networks (ConvNets) suited for inference tasks deployed on resource-constrained devices at the edge of the…

Human motion prediction is an increasingly interesting topic in computer vision and robotics. In this paper, we propose a new 2D CNN based network, TrajectoryNet, to predict future poses in the trajectory space. Compared with most existing…

In recent times, learning-based methods for video deraining have demonstrated commendable results. However, there are two critical challenges that these methods are yet to address: exploiting temporal correlations among adjacent frames and…

Efficiency is an important issue in designing video architectures for action recognition. 3D CNNs have witnessed remarkable progress in action recognition from videos. However, compared with their 2D counterparts, 3D convolutions often…

Existing stereo matching networks typically rely on either cost-volume construction based on 3D convolutions or deformation methods based on iterative optimization. The former incurs significant computational overhead during cost…

This work proposes a new end-to-end DCNN based approach for motion segmentation, especially for video sequences captured with such non-static cameras, called MOSNET. While other approaches focus on spatial or temporal context only, the…

As a challenging task of high-level video understanding, weakly supervised temporal action localization has been attracting increasing attention. With only video annotations, most existing methods seek to handle this task with a…

Designing effective architectures is one of the key factors behind the success of deep neural networks. Existing deep architectures are either manually designed or automatically searched by some Neural Architecture Search (NAS) methods.…

Temporal action localization is an important and challenging task that aims to locate temporal regions in real-world untrimmed videos where actions occur and recognize their classes. It is widely acknowledged that video context is a…

Object detection is a fundamental and challenging problem in aerial and satellite image analysis. More recently, a two-stage detector Faster R-CNN is proposed and demonstrated to be a promising tool for object detection in optical remote…

Algorithms for video action recognition should consider not only spatial information but also temporal relations, which remains challenging. We propose a 3D-CNN-based action recognition model, called the blockwise temporal-spatial path-way…

Foundation models have impressive performance and generalization capabilities across a wide range of applications. The increasing size of the models introduces great challenges for the training. Tensor parallelism is a critical technique…