Related papers: Alternative Semantic Representations for Zero-Shot…

With advances in data-driven machine learning research, a wide variety of prediction models have been proposed to capture spatio-temporal features for the analysis of video streams. Recognising actions and detecting action transitions…

This paper presents a novel method for learning a pose lexicon comprising semantic poses defined by textual instructions and their associated visual poses defined by visual features. The proposed method simultaneously takes two input…

The number of categories for action recognition is growing rapidly and it has become increasingly hard to label sufficient training data for learning conventional models for all categories. Instead of collecting ever more data and labelling…

In this paper we propose a non-metric ranking-based representation of semantic similarity that allows natural aggregation of semantic information from multiple heterogeneous sources. We apply the ranking-based representation to zero-shot…

Text-based person search aims to retrieve images of a certain pedestrian by a textual description. The key challenge of this task is to eliminate the inter-modality gap and achieve the feature alignment across modalities. In this paper, we…

How does one represent an action? How does one describe an action that we have never seen before? Such questions are addressed by the Zero Shot Learning paradigm, where a model is trained on only a subset of classes and is evaluated on its…

Human action recognition refers to automatic recognizing human actions from a video clip. In reality, there often exist multiple human actions in a video stream. Such a video stream is often weakly-annotated with a set of relevant human…

This work aims to present novel description methods for human action recognition. Generally, a video sequence can be represented as a collection of spatial temporal words by detecting space-time interest points and describing the unique…

Zero-shot learning has gained popularity due to its potential to scale recognition models without requiring additional training data. This is usually achieved by associating categories with their semantic information like attributes.…

Learning visual representations from observing actions to benefit robot visuo-motor policy generation is a promising direction that closely resembles human cognitive function and perception. Motivated by this, and further inspired by…

We propose a novel approach to improve a visual-semantic embedding model by incorporating concept representations captured from an external structured knowledge base. We investigate its performance on image classification under both…

Visual localization is a useful alternative to standard localization techniques. It works by utilizing cameras. In a typical scenario, features are extracted from captured images and compared with geo-referenced databases. Location…

In this paper, we propose a novel single image action recognition algorithm which is based on the idea of semantic body part actions. Unlike existing bottom up methods, we argue that the human action is a combination of meaningful body part…

Few-shot action recognition aims to address the high cost and impracticality of manually labeling complex and variable video data in action recognition. It requires accurately classifying human actions in videos using only a few labeled…

Skeleton-based human action recognition has been drawing more interest recently due to its low sensitivity to appearance changes and the accessibility of more skeleton data. However, even the 3D skeletons captured in practice are still…

In this dissertation, I present my work towards exploring temporal information for better video understanding. Specifically, I have worked on two problems: action recognition and semantic segmentation. For action recognition, I have…

Event camera is an asynchronous, high frequency vision sensor with low power consumption, which is suitable for human action understanding task. It is vital to encode the spatial-temporal information of event data properly and use standard…

This work focuses on the semantic relations between scenes and objects for visual object recognition. Semantic knowledge can be a powerful source of information especially in scenarios with few or no annotated training samples. These…

Knowledge transfer, zero-shot learning and semantic image retrieval are methods that aim at improving accuracy by utilizing semantic information, e.g. from WordNet. It is assumed that this information can augment or replace missing visual…

The existing image feature extraction methods are primarily based on the content and structure information of images, and rarely consider the contextual semantic information. Regarding some types of images such as scenes and objects, the…