Related papers: TARN: Temporal Attentive Relation Network for Few-…

Few-shot action recognition has attracted increasing attention due to the difficulty in acquiring the properly labelled training samples. Current works have shown that preserving spatial information and comparing video descriptors are…

Metric-based learning is a well-known family of methods for few-shot learning, especially in computer vision. Recently, they have been used in many natural language processing applications but not for slot tagging. In this paper, we explore…

Typical techniques for video captioning follow the encoder-decoder framework, which can only focus on one source video being processed. A potential disadvantage of such design is that it cannot capture the multiple visual context…

Deep neural networks (DNNs) have achieved state-of-the-art results on time series classification (TSC) tasks. In this work, we focus on leveraging DNNs in the often-encountered practical scenario where access to labeled training data is…

The objective of this paper is a temporal alignment network that ingests long term video sequences, and associated text sentences, in order to: (1) determine if a sentence is alignable with the video; and (2) if it is alignable, then…

Although various image-based domain adaptation (DA) techniques have been proposed in recent years, domain shift in videos is still not well-explored. Most previous works only evaluate performance on small-scale datasets which are saturated.…

Conventional methods for object detection typically require a substantial amount of training data and preparing such high-quality training data is very labor-intensive. In this paper, we propose a novel few-shot object detection network…

We present an approach for weakly supervised learning of human actions. Given a set of videos and an ordered list of the occurring actions, the goal is to infer start and end frames of the related action classes within the video and to…

Most action recognition models treat human activities as unitary events. However, human activities often follow a certain hierarchy. In fact, many human activities are compositional. Also, these actions are mostly human-object interactions.…

We propose MASTAF, a Model-Agnostic Spatio-Temporal Attention Fusion network for few-shot video classification. MASTAF takes input from a general video spatial and temporal representation,e.g., using 2D CNN, 3D CNN, and Video Transformer.…

It has been well recognized that modeling human-object or object-object relations would be helpful for detection task. Nevertheless, the problem is not trivial especially when exploring the interactions between human actor, object and scene…

We propose a Few-shot Learning pipeline for 3D skeleton-based action recognition by Joint tEmporal and cAmera viewpoiNt alIgnmEnt (JEANIE). To factor out misalignment between query and support sequences of 3D body joints, we propose an…

The action anticipation task refers to predicting what action will happen based on observed videos, which requires the model to have a strong ability to summarize the present and then reason about the future. Experience and common sense…

This technical report presents our solution for temporal action detection task in AcitivityNet Challenge 2021. The purpose of this task is to locate and identify actions of interest in long untrimmed videos. The crucial challenge of the…

Human Activity Recognition (HAR) using deep neural network has become a hot topic in human-computer interaction. Machine can effectively identify human naturalistic activities by learning from a large collection of sensor data. Activity…

We present Temporal Aggregation Network (TAN) which decomposes 3D convolutions into spatial and temporal aggregation blocks. By stacking spatial and temporal convolutions repeatedly, TAN forms a deep hierarchical representation for…

Temporal language grounding in videos aims to localize the temporal span relevant to the given query sentence. Previous methods treat it either as a boundary regression task or a span extraction task. This paper will formulate temporal…

Video-based person re-identification (re-ID) refers to matching people across camera views from arbitrary unaligned video footages. Existing methods rely on supervision signals to optimise a projected space under which the distances between…

Few-shot action recognition (FSAR) requires models to generalize to novel action categories from only a handful of annotated samples. Despite progress with vision-language models, existing approaches still suffer from semantic-temporal…

Although Graph Neural Networks (GNNs) have been successful in node classification tasks, their performance heavily relies on the availability of a sufficient number of labeled nodes per class. In real-world situations, not all classes have…