Related papers: Spatio-Temporal Attention for Consistent Video Sem…
Spatio-temporal forecasting is an open research field whose interest is growing exponentially. In this work we focus on creating a complex deep neural framework for spatio-temporal traffic forecasting with comparatively very good…
High level understanding of sequential visual input is important for safe and stable autonomy, especially in localization and object detection. While traditional object classification and tracking approaches are specifically designed to…
We present a convolution-free approach to video classification built exclusively on self-attention over space and time. Our method, named "TimeSformer," adapts the standard Transformer architecture to video by enabling spatiotemporal…
It remains challenging to automatically predict the multi-agent trajectory due to multiple interactions including agent to agent interaction and scene to agent interaction. Although recent methods have achieved promising performance, most…
This paper studies how to introduce viewpoint-invariant feature representations that can help action recognition and detection. Although we have witnessed great progress of action recognition in the past decade, it remains challenging yet…
Channel and spatial attention mechanisms introduced by earlier works enhance the representation abilities of deep convolutional neural networks (CNNs) but often lead to increased parameter and computation costs. While recent approaches…
With the rising focus on quadrupeds, a generalized policy capable of handling different robot models and sensor inputs becomes highly beneficial. Although several methods have been proposed to address different morphologies, it remains a…
Recognizing human actions from untrimmed videos is an important task in activity understanding, and poses unique challenges in modeling long-range temporal relations. Recent works adopt a predict-and-refine strategy which converts an…
Many road accidents occur due to distracted drivers. Today, driver monitoring is essential even for the latest autonomous vehicles to alert distracted drivers in order to take over control of the vehicle in case of emergency. In this paper,…
This paper studies introducing viewpoint invariant feature representations in existing action recognition architecture. Despite significant progress in action recognition, efficiently handling geometric variations in large-scale datasets…
Video semantic segmentation has achieved great progress under the supervision of large amounts of labelled training data. However, domain adaptive video segmentation, which can mitigate data labelling constraints by adapting from a labelled…
Despite the significant progress made by deep learning in natural image matting, there has been so far no representative work on deep learning for video matting due to the inherent technical challenges in reasoning temporal domain and lack…
Detectors with high coverage have direct and far-reaching benefits for road users in route planning and avoiding traffic congestion, but utilizing these data presents unique challenges including: the dynamic temporal correlation, and the…
Spiking neural networks (SNNs) mimic brain computational strategies, and exhibit substantial capabilities in spatiotemporal information processing. As an essential factor for human perception, visual attention refers to the dynamic process…
In this paper, we introduce spatial attention for refining the information in multi-direction neural beamformer for far-field automatic speech recognition. Previous approaches of neural beamformers with multiple look directions, such as the…
Existing state-of-the-art methods for surgical phase recognition either rely on the extraction of spatial-temporal features at a short-range temporal resolution or adopt the sequential extraction of the spatial and temporal features across…
Sound event localization and detection (SELD) is a task for the classification of sound events and the localization of direction of arrival (DoA) utilizing multichannel acoustic signals. Prior studies employ spectral and channel information…
Devising intelligent agents able to live in an environment and learn by observing the surroundings is a longstanding goal of Artificial Intelligence. From a bare Machine Learning perspective, challenges arise when the agent is prevented…
This paper aims to accelerate video stream processing, such as object detection and semantic segmentation, by leveraging the temporal redundancies that exist between video frames. Instead of propagating and warping features using motion…
To empower the iterative assessments involved during a person's rehabilitation, automated assessment of a person's abilities during daily activities requires temporally precise segmentation of fine-grained actions in therapy videos.…