Related papers: SSAN: Separable Self-Attention Network for Video R…
This paper presents a novel approach for the Vision-and-Language Navigation (VLN) task in continuous 3D environments, which requires an autonomous agent to follow natural language instructions in unseen environments. Existing end-to-end…
We present a novel technique for self-supervised video representation learning by: (a) decoupling the learning objective into two contrastive subtasks respectively emphasizing spatial and temporal features, and (b) performing it…
Spatiotemporal learning is challenging due to the intricate interplay between spatial and temporal dependencies, the high dimensionality of the data, and scalability constraints. These challenges are further amplified in scientific domains,…
Temporal segmentation of long videos is an important problem, that has largely been tackled through supervised learning, often requiring large amounts of annotated training data. In this paper, we tackle the problem of self-supervised…
Traffic forecasting is one canonical example of spatial-temporal learning task in Intelligent Traffic System. Existing approaches capture spatial dependency with a pre-determined matrix in graph convolution neural operators. However, the…
Self-supervised representation learning of Multivariate Time Series (MTS) is a challenging task and attracts increasing research interests in recent years. Many previous works focus on the pretext task of self-supervised learning and…
Space-time self-similarity (STSS), which captures visual correspondences across frames, provides an effective way to represent temporal dynamics for video understanding. In this work, we explore higher-order STSS and demonstrate how STSSs…
This study introduces an enhanced approach to video super-resolution by extending ordinary Single-Image Super-Resolution (SISR) Super-Resolution Generative Adversarial Network (SRGAN) structure to handle spatio-temporal data. While SRGAN…
Action recognition is a critical task in video understanding, requiring the comprehensive capture of spatio-temporal cues across various scales. However, existing methods often overlook the multi-granularity nature of actions. To address…
Given a video, video grounding aims to retrieve a temporal moment that semantically corresponds to a language query. In this work, we propose a Parallel Attention Network with Sequence matching (SeqPAN) to address the challenges in this…
Self-supervised pre-training paradigms have been extensively explored in the field of skeleton-based action recognition. In particular, methods based on masked prediction have pushed the performance of pre-training to a new height. However,…
The recent surge in video generation has shown the growing demand for high-quality video synthesis using large vision models. Existing video generation models are predominantly based on the video diffusion transformer (vDiT), however, they…
Convolution has been arguably the most important feature transform for modern neural networks, leading to the advance of deep learning. Recent emergence of Transformer networks, which replace convolution layers with self-attention blocks,…
Contrastive learning of auditory and visual perception has been extremely successful when investigated individually. However, there are still major questions on how we could integrate principles learned from both domains to attain effective…
We propose a novel deep structured learning framework for event temporal relation extraction. The model consists of 1) a recurrent neural network (RNN) to learn scoring functions for pair-wise relations, and 2) a structured support vector…
Contextual information provides important cues for disambiguating visually similar pixels in scene segmentation. In this paper, we introduce a neuron-level Selective Context Aggregation (SCA) module for scene segmentation, comprised of a…
There is significant progress in recognizing traditional human activities from videos focusing on highly distinctive actions involving discriminative body movements, body-object and/or human-human interactions. Driver's activities are…
Many real-world applications involve multivariate, geo-tagged time series data: at each location, multiple sensors record corresponding measurements. For example, air quality monitoring system records PM2.5, CO, etc. The resulting…
We propose a self-supervised approach for learning representations and robotic behaviors entirely from unlabeled videos recorded from multiple viewpoints, and study how this representation can be used in two robotic imitation settings:…
Spiking Neural Networks (SNNs), renowned for their low power consumption, brain-inspired architecture, and spatio-temporal representation capabilities, have garnered considerable attention in recent years. Similar to Artificial Neural…