Related papers: Late Temporal Modeling in 3D CNN Architectures wit…
We introduce the Temporal Contrastive Transformer (TCT), a representation learning framework designed to capture contextual temporal dynamics in sequences of financial transactions. The model is trained using a self-supervised contrastive…
Existing studies for gait recognition are dominated by in-the-lab scenarios. Since people live in real-world senses, gait recognition in the wild is a more practical problem that has recently attracted the attention of the community of…
Transformer-based models have shown strong performance in time-series forecasting by leveraging self-attention to model long-range temporal dependencies. However, their effectiveness depends critically on the quality and structure of input…
While Transformers have achieved promising results in end-to-end (E2E) automatic speech recognition (ASR), their autoregressive (AR) structure becomes a bottleneck for speeding up the decoding process. For real-world deployment, ASR systems…
Motivated by the success of Transformers in natural language processing (NLP) tasks, there emerge some attempts (e.g., ViT and DeiT) to apply Transformers to the vision domain. However, pure Transformer architectures often require a large…
We present a new method for finding video CNN architectures that capture rich spatio-temporal information in videos. Previous work, taking advantage of 3D convolutions, obtained promising results by manually designing video CNN…
Human action recognition is regarded as a key cornerstone in domains such as surveillance or video understanding. Despite recent progress in the development of end-to-end solutions for video-based action recognition, achieving…
Attention-based beamformers have recently been shown to be effective for multi-channel speech recognition. However, they are less capable at capturing local information. In this work, we propose a 2D Conv-Attention module which combines…
Skeleton-based gesture recognition methods have achieved high success using Graph Convolutional Network (GCN). In addition, context-dependent adaptive topology as a neighborhood vertex information and attention mechanism leverages a model…
Transformer attention architectures, similar to those developed for natural language processing, have recently proved efficient also in vision, either in conjunction with or as a replacement for convolutional layers. Typically, visual…
We present a module that extends the temporal graph of a graph convolutional network (GCN) for action recognition with a sequence of skeletons. Existing methods attempt to represent a more appropriate spatial graph on an intra-frame, but…
Active vision is inherently attention-driven: The agent actively selects views to attend in order to fast achieve the vision task while improving its internal representation of the scene being observed. Inspired by the recent success of…
A collection of approaches based on graph convolutional networks have proven success in skeleton-based action recognition by exploring neighborhood information and dense dependencies between intra-frame joints. However, these approaches…
In this paper, we propose a long-sequence modeling framework, named StreamPETR, for multi-view 3D object detection. Built upon the sparse query design in the PETR series, we systematically develop an object-centric temporal mechanism. The…
Consider a set of n images of a scene with dynamic objects captured with a static or a handheld camera. Let the temporal order in which these images are captured be unknown. There can be n! possibilities for the temporal order in which…
The success of deep learning methods led to significant breakthroughs in 3-D point cloud processing tasks with applications in remote sensing. Existing methods utilize convolutions that have some limitations, as they assume a uniform input…
This paper describes a language representation model which combines the Bidirectional Encoder Representations from Transformers (BERT) learning mechanism described in Devlin et al. (2018) with a generalization of the Universal Transformer…
This paper presents our approach to the third YouTube-8M video understanding competition that challenges par-ticipants to localize video-level labels at scale to the pre-cise time in the video where the label actually occurs. Ourmodel is an…
We address the task of supervised action segmentation which aims to partition a video into non-overlapping segments, each representing a different action. Recent works apply transformers to perform temporal modeling at the frame-level,…
Inductive representation learning on temporal graphs is an important step toward salable machine learning on real-world dynamic networks. The evolving nature of temporal dynamic graphs requires handling new nodes as well as capturing…