Related papers: Pyramid Region-based Slot Attention Network for Te…
Long-range and short-range temporal modeling are two complementary and crucial aspects of video recognition. Most of the state-of-the-arts focus on short-range spatio-temporal modeling and then average multiple snippet-level predictions to…
Contextual information plays an important role in action recognition. Local operations have difficulty to model the relation between two elements with a long-distance interval. However, directly modeling the contextual information between…
Partially Relevant Video Retrieval (PRVR) is a practical yet challenging task that involves retrieving videos based on queries relevant to only specific segments. While existing works follow the paradigm of developing models to process…
Deep convolutional neural networks (DCNNs) have achieved great success in monocular depth estimation (MDE). However, few existing works take the contributions for MDE of different levels feature maps into account, leading to inaccurate…
In recent years, few-shot action recognition has achieved remarkable performance through spatio-temporal relation modeling. Although a wide range of spatial and temporal alignment modules have been proposed, they primarily address spatial…
Objective: To enable context-aware computer assistance in the operating room of the future, cognitive systems need to understand automatically which surgical phase is being performed by the medical team. The primary source of information…
This paper proposes a novel deep learning-based video object matting method that can achieve temporally coherent matting results. Its key component is an attention-based temporal aggregation module that maximizes image matting networks'…
Triggered by the success of transformers in various visual tasks, the spatial self-attention mechanism has recently attracted more and more attention in the computer vision community. However, we empirically found that a typical vision…
Many video analysis tasks require temporal localization thus detection of content changes. However, most existing models developed for these tasks are pre-trained on general video action classification tasks. This is because large scale…
Few-shot temporal action localization (TAL) methods that adapt large models via single-prompt tuning often fail to produce precise temporal boundaries. This stems from the model learning a non-discriminative mean representation of an action…
A lack of corpora has so far limited advances in integrating human gaze data as a supervisory signal in neural attention mechanisms for natural language processing(NLP). We propose a novel hybrid text saliency model(TSM) that, for the first…
Sign language translation (SLT) aims to interpret sign video sequences into text-based natural language sentences. Sign videos consist of continuous sequences of sign gestures with no clear boundaries in between. Existing SLT models usually…
A primary challenge faced in few-shot action recognition is inadequate video data for training. To address this issue, current methods in this field mainly focus on devising algorithms at the feature level while little attention is paid to…
In this technical report, we describe our solution to temporal action proposal (task 1) in ActivityNet Challenge 2019. First, we fine-tune a ResNet-50-C3D CNN on ActivityNet v1.3 based on Kinetics pretrained model to extract snippet-level…
Temporal sentence grounding (TSG) aims to identify the temporal boundary of a specific segment from an untrimmed video by a sentence query. All existing works first utilize a sparse sampling strategy to extract a fixed number of video…
As industrial systems become more complex and monitoring sensors for everything from surveillance to our health become more ubiquitous, multivariate time series prediction is taking an important place in the smooth-running of our society. A…
Recent advances in computer vision have made it possible to automatically assess from videos the manipulation skills of humans in performing a task, which breeds many important applications in domains such as health rehabilitation and…
Semantic segmentation is a vital task in the field of remote sensing (RS). However, conventional convolutional neural network (CNN) and transformer-based models face limitations in capturing long-range dependencies or are often…
In this paper, we consider the problem of temporal action localization under low-shot (zero-shot & few-shot) scenario, with the goal of detecting and classifying the action instances from arbitrary categories within some untrimmed videos,…
Point-level weakly-supervised temporal action localization (PWTAL) aims to localize actions with only a single timestamp annotation for each action instance. Existing methods tend to mine dense pseudo labels to alleviate the label sparsity,…