Related papers: C-DLinkNet: considering multi-level semantic featu…

Large Language Models (LLMs) have shown remarkable proficiency in natural language understanding (NLU), opening doors for innovative applications. We introduce StreamLink - an LLM-driven distributed data system designed to improve the…

Wireframe parsing aims to recover line segments and their junctions to form a structured geometric representation useful for downstream tasks such as Simultaneous Localization and Mapping (SLAM). Existing methods predict lines and junctions…

Person re-identification is a challenging task due to various complex factors. Recent studies have attempted to integrate human parsing results or externally defined attributes to help capture human parts or important object regions. On the…

This paper presents an approach to parsing humans when there is significant occlusion. We model humans using a graphical model which has a tree structure building on recent work [32, 6] and exploit the connectivity prior that, even in…

Eye-tracking data reveals valuable insights into users' cognitive states but is difficult to analyze due to its structured, non-linguistic nature. While large language models (LLMs) excel at reasoning over text, they struggle with temporal…

In contrast to the abundant research focusing on large-scale models, the progress in lightweight semantic segmentation appears to be advancing at a comparatively slower pace. However, existing compact methods often suffer from limited…

Semantic segmentation has made significant strides in pixel-level image understanding, yet it remains limited in capturing contextual and semantic relationships between objects. Current models, such as CNN and Transformer-based…

Instance-level human parsing towards real-world human analysis scenarios is still under-explored due to the absence of sufficient data resources and technical difficulty in parsing multiple instances in a single pass. Several related works…

Keypoints of objects reflect their concise abstractions, while the corresponding connection links (CL) build the skeleton by detecting the intrinsic relations between keypoints. Existing approaches are typically computationally-intensive,…

Existing works on semantic segmentation typically consider a small number of labels, ranging from tens to a few hundreds. With a large number of labels, training and evaluation of such task become extremely challenging due to correlation…

Humans tend to decompose a sentence into different parts like \textsc{sth do sth at someplace} and then fill each part with certain content. Inspired by this, we follow the \textit{principle of modular design} to propose a novel image…

Deep learning based methods hold state-of-the-art results in low-level image processing tasks, but remain difficult to interpret due to their black-box construction. Unrolled optimization networks present an interpretable alternative to…

Training deep models for semantic scene completion (SSC) is challenging due to the sparse and incomplete input, a large quantity of objects of diverse scales as well as the inherent label noise for moving objects. To address the…

Modern supervised semantic segmentation methods are usually finetuned based on the supervised or self-supervised models pre-trained on ImageNet. Recent work shows that transferring the knowledge from CLIP to semantic segmentation via prompt…

Human body parsing remains a challenging problem in natural scenes due to multi-instance and inter-part semantic confusions as well as occlusions. This paper proposes a novel approach to decomposing multiple human bodies into semantic part…

Current high-performance semantic segmentation models are purely data-driven sub-symbolic approaches and blind to the structured nature of the visual world. This is in stark contrast to human cognition which abstracts visual perceptions at…

The key challenge in semantic search is to create models that are both accurate and efficient in pinpointing relevant sentences for queries. While BERT-style bi-encoders excel in efficiency with pre-computed embeddings, they often miss…

Vision-based person, hand or face detection approaches have achieved incredible success in recent years with the development of deep convolutional neural network (CNN). In this paper, we take the inherent correlation between the body and…

Forms are a common type of document in real life and carry rich information through textual contents and the organizational structure. To realize automatic processing of forms, word grouping and relation extraction are two fundamental and…

Large language models (LLMs) can handle a wide variety of general tasks with simple prompts, without the need for task-specific training. Multimodal Large Language Models (MLLMs), built upon LLMs, have demonstrated impressive potential in…