Related papers: Capturing and Sharing Know-How through Visual Proc…

Discovery and learning of an underlying spatiotemporal hierarchy in sequential data is an important topic for machine learning. Despite this, little work has been done to explore hierarchical generative models that can flexibly adapt their…

Visual place recognition (VPR) is usually considered as a specific image retrieval problem. Limited by existing training frameworks, most deep learning-based works cannot extract sufficiently stable global features from RGB images and rely…

Visual Place Recognition (VPR) aims to retrieve frames from a geotagged database that are located at the same place as the query frame. To improve the robustness of VPR in perceptually aliasing scenarios, sequence-based VPR methods are…

State-of-the-art vision-language models (VLMs) still have limited performance in structural knowledge extraction, such as relations between objects. In this work, we present ViStruct, a training framework to learn VLMs for effective visual…

Video Class-Incremental Learning (VCIL) seeks to develop models that continuously learn new action categories over time without forgetting previously acquired knowledge. Unlike traditional Class-Incremental Learning (CIL), VCIL introduces…

Continual learning enables pre-trained generative vision-language models (VLMs) to incorporate knowledge from new tasks without retraining data from previous ones. Recent methods update a visual projector to translate visual information for…

It is always demanding to learn robust visual representation for various learning problems; however, this learning and maintenance process usually suffers from noise, incompleteness or knowledge domain mismatch. Thus, robust representation…

Vision foundation models (VFMs) are predominantly developed using data-centric methods. These methods require training on vast amounts of data usually with high-quality labels, which poses a bottleneck for most institutions that lack both…

Humans can visualize new and unknown concepts from their natural language description, based on their experience and previous knowledge. Insipired by this, we present a way to extend this ability to Vision-Language Models (VLMs), teaching…

Recently, Visual Programming (VProg) has emerged as a significant framework for visual reasoning (VR) tasks due to its interpretability and cross-task generality. However, even with invoking powerful pre-trained Vision-Language models…

Accreditation bodies call for curriculum development processes open to all stakeholders, reflecting viewpoints of students, industry, university faculty and society. However, communication difficulties between faculty and non-faculty groups…

Visual place recognition (VPR) is an essential component of many autonomous and augmented/virtual reality systems. It enables the systems to robustly localize themselves in large-scale environments. Existing VPR methods demonstrate…

Vision-language models (VLMs) have achieved remarkable success across multimodal tasks, yet their substantial computational demands hinder efficient deployment. Knowledge distillation (KD) has emerged as a powerful approach for building…

This paper presents a groundbreaking multimodal, multi-task, multi-teacher joint-grained knowledge distillation model for visually-rich form document understanding. The model is designed to leverage insights from both fine-grained and…

Knowledge Distillation refers to a class of methods that transfers the knowledge from a teacher network to a student network. In this paper, we propose Sparse Representation Matching (SRM), a method to transfer intermediate knowledge…

Visual Place Recognition (VPR) in long-term deployment requires reasoning beyond pixel similarity: systems must make transparent, interpretable decisions that remain robust under lighting, weather and seasonal change. We present Text2Graph…

Background: A systematic literature review (SLR) is a methodology used to aggregate all relevant existing evidence to answer a research question of interest. Although crucial, the process used to select primary studies can be arduous, time…

Pre-trained language models are still far from human performance in tasks that need understanding of properties (e.g. appearance, measurable quantity) and affordances of everyday objects in the real world since the text lacks such…

Document layout analysis is crucial for understanding document structures. On this task, vision and semantics of documents, and relations between layout components contribute to the understanding process. Though many works have been…

Diffusion-based models have been widely used in various visual generation tasks, showing promising results in image super-resolution (SR), while typically being limited by dozens or even hundreds of sampling steps. Although existing methods…