Related papers: SAFCAR: Structured Attention Fusion for Compositio…
In this paper we revisit feature fusion, an old-fashioned topic, in the new context of text-to-video retrieval. Different from previous research that considers feature fusion only at one end, let it be video or text, we aim for feature…
Humans are highly efficient learners, with the ability to grasp the meaning of a new concept from just a few examples. Unlike popular computer vision systems, humans can flexibly leverage the compositional structure of the visual world,…
Skeleton-based action segmentation requires recognizing composable actions in untrimmed videos. Current approaches decouple this problem by first extracting local visual features from skeleton sequences and then processing them by a…
We present a general framework based on weighted finite automata and weighted finite-state transducers for describing and implementing speech recognizers. The framework allows us to represent uniformly the information sources and data…
Dialogue Act Recognition (DAR) is a challenging problem in dialogue interpretation, which aims to attach semantic labels to utterances and characterize the speaker's intention. Currently, many existing approaches formulate the DAR problem…
When autonomous agents observe different domains of a shared environment, each signal they exchange mixes relevant and irrelevant dimensions. No existing mechanism lets the receiver evaluate which dimensions to absorb. We introduce…
By extracting spatial and temporal characteristics in one network, the two-stream ConvNets can achieve the state-of-the-art performance in action recognition. However, such a framework typically suffers from the separately processing of…
Videos of actions are complex signals containing rich compositional structure in space and time. Current video generation methods lack the ability to condition the generation on multiple coordinated and potentially simultaneous timed…
We present PAT, a transformer-based network that learns complex temporal co-occurrence action dependencies in a video by exploiting multi-scale temporal features. In existing methods, the self-attention mechanism in transformers loses the…
Human Activity Recognition from body-worn sensor data poses an inherent challenge in capturing spatial and temporal dependencies of time-series signals. In this regard, the existing recurrent or convolutional or their hybrid models for…
Action localization networks are often structured as a feature encoder sub-network and a localization sub-network, where the feature encoder learns to transform an input video to features that are useful for the localization sub-network to…
Humans are remarkably flexible when understanding new sentences that include combinations of concepts they have never encountered before. Recent work has shown that while deep networks can mimic some human language abilities when presented…
There are many realistic applications of activity recognition where the set of potential activity descriptions is combinatorially large. This makes end-to-end supervised training of a recognition system impractical as no training set is…
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…
Autonomous agents need large repertoires of skills to act reasonably on new tasks that they have not seen before. However, acquiring these skills using only a stream of high-dimensional, unstructured, and unlabeled observations is a tricky…
Despite the central role of action in embodied intelligence, learning transferable action representations from visual transitions remains a fundamental challenge, particularly when world models must generalize across embodiments under…
This paper introduces a novel approach to Social Group Activity Recognition (SoGAR) using Self-supervised Transformers network that can effectively utilize unlabeled video data. To extract spatio-temporal information, we created local and…
Deep neural networks based purely on attention have been successful across several domains, relying on minimal architectural priors from the designer. In Human Action Recognition (HAR), attention mechanisms have been primarily adopted on…
Sensor fusion of camera, LiDAR, and 4-dimensional (4D) Radar has brought a significant performance improvement in autonomous driving. However, there still exist fundamental challenges: deeply coupled fusion methods assume continuous sensor…
Temporal action detection (TAD) aims to detect the semantic labels and boundaries of action instances in untrimmed videos. Current mainstream approaches are multi-step solutions, which fall short in efficiency and flexibility. In this…