Related papers: Global2Local: Efficient Structure Search for Video…
Fully supervised action segmentation works on frame-wise action recognition with dense annotations and often suffers from the over-segmentation issue. Existing works have proposed a variety of solutions such as boundary-aware networks,…
Instance segmentation is a challenging task aiming at classifying and segmenting all object instances of specific classes. While two-stage box-based methods achieve top performances in the image domain, they cannot easily extend their…
Despite the success of deep learning for static image understanding, it remains unclear what are the most effective network architectures for the spatial-temporal modeling in videos. In this paper, in contrast to the existing CNN+RNN or…
In interactive object segmentation a user collaborates with a computer vision model to segment an object. Recent works employ convolutional neural networks for this task: Given an image and a set of corrections made by the user as input,…
Active localization is the problem of generating robot actions that allow it to maximally disambiguate its pose within a reference map. Traditional approaches to this use an information-theoretic criterion for action selection and…
Recent advances in pixel-level tasks (e.g. segmentation) illustrate the benefit of of long-range interactions between aggregated region-based representations that can enhance local features. However, such aggregated representations, often…
Temporal action localization presents a trade-off between test performance and annotation-time cost. Fully supervised methods achieve good performance with time-consuming boundary annotations. Weakly supervised methods with cheaper…
Learning representations that accurately capture long-range dependencies in sequential inputs -- including text, audio, and genomic data -- is a key problem in deep learning. Feed-forward convolutional models capture only feature…
We propose `Hide-and-Seek', a weakly-supervised framework that aims to improve object localization in images and action localization in videos. Most existing weakly-supervised methods localize only the most discriminative parts of an object…
Video moment retrieval aims to search the moment most relevant to a given language query. However, most existing methods in this community often require temporal boundary annotations which are expensive and time-consuming to label. Hence…
Detecting actions in untrimmed videos is an important yet challenging task. In this paper, we present the structured segment network (SSN), a novel framework which models the temporal structure of each action instance via a structured…
Salient object detection requires a comprehensive and scalable receptive field to locate the visually significant objects in the image. Recently, the emergence of visual transformers and multi-branch modules has significantly enhanced the…
Precise video retrieval requires multi-modal correlations to handle unseen vocabulary and scenes, becoming more complex for lengthy videos where models must perform effectively without prior training on a specific dataset. We introduce a…
Graph-based representations such as Scene Graphs enable localization in structured indoor environments by matching a locally observed graph, constructed from sensor data, to a prior map. This process is particularly challenging in…
The Learnable Tree Filter presents a remarkable approach to model structure-preserving relations for semantic segmentation. Nevertheless, the intrinsic geometric constraint forces it to focus on the regions with close spatial distance,…
Segmentation of ultra-high resolution images is increasingly demanded, yet poses significant challenges for algorithm efficiency, in particular considering the (GPU) memory limits. Current approaches either downsample an ultra-high…
We propose an efficient method to learn deep local descriptors for instance-level recognition. The training only requires examples of positive and negative image pairs and is performed as metric learning of sum-pooled global image…
Deep learning models, in particular \textit{image} models, have recently gained generalisability and robustness. %are becoming more general and robust by the day. In this work, we propose to exploit such advances in the realm of…
A major focus of current research on place recognition is visual localization for autonomous driving. In this scenario, as cameras will be operating continuously, it is realistic to expect videos as an input to visual localization…
Action scene understanding in soccer is a challenging task due to the complex and dynamic nature of the game, as well as the interactions between players. This article provides a comprehensive overview of this task divided into action…