Related papers: TSP-Transformer: Task-Specific Prompts Boosted Tra…

Scene understanding remains a significant challenge in the computer vision community. The visual psychophysics literature has demonstrated the importance of interdependence among parts of the scene. Yet, the majority of methods in computer…

Parameter efficient transfer learning (PETL) is an emerging research spot that aims to adapt large-scale pre-trained models to downstream tasks. Recent advances have achieved great success in saving storage and computation costs. However,…

Cross-modal medical image translation is an essential task for synthesizing missing modality data for clinical diagnosis. However, current learning-based techniques have limitations in capturing cross-modal and global features, restricting…

Table structure recognition (TSR) aims to convert tabular images into a machine-readable format. Although hybrid convolutional neural network (CNN)-transformer architecture is widely used in existing approaches, linear projection…

Manipulating images of complex scenes to reconstruct, insert and/or remove specific object instances is a challenging task. Complex scenes contain multiple semantics and objects, which are frequently cluttered or ambiguous, thus hampering…

Previous multi-task dense prediction studies developed complex pipelines such as multi-modal distillations in multiple stages or searching for task relational contexts for each task. The core insight beyond these methods is to maximize the…

Effective learning of spatial-temporal information within a point cloud sequence is highly important for many down-stream tasks such as 4D semantic segmentation and 3D action recognition. In this paper, we propose a novel framework named…

Convolutional neural networks (CNNs) have been widely used in various vision tasks, e.g. image classification, semantic segmentation, etc. Unfortunately, standard 2D CNNs are not well suited for spherical signals such as panorama images or…

Spatial Transformer Networks (STNs) estimate image transformations that can improve downstream tasks by `zooming in' on relevant regions in an image. However, STNs are hard to train and sensitive to mis-predictions of transformations. To…

This paper investigates a fundamental problem of scene understanding: how to parse a scene image into a structured configuration (i.e., a semantic object hierarchy with object interaction relations). We propose a deep architecture…

Learning from large-scale pre-trained models with strong generalization ability has shown remarkable success in a wide range of downstream tasks recently, but it is still underexplored in the challenging few-shot class-incremental learning…

Transformer plays a central role in many fundamental deep learning models, e.g., the ViT in computer vision and the BERT and GPT in natural language processing, whose effectiveness is mainly attributed to its multi-head attention (MHA)…

In this work, we introduce the Prototypical Transformer (ProtoFormer), a general and unified framework that approaches various motion tasks from a prototype perspective. ProtoFormer seamlessly integrates prototype learning with Transformer…

Text classification is one of the most imperative tasks in natural language processing (NLP). Recent advances with pre-trained language models (PLMs) have shown remarkable success on this task. However, the satisfying results obtained by…

Segment Anything Models (SAMs) like SEEM and SAM have demonstrated great potential in learning to segment anything. The core design of SAMs lies with Promptable Segmentation, which takes a handcrafted prompt as input and returns the…

Few-Shot Learning (FSL) aims to recognize new classes with limited labeled data. Recent studies have attempted to address the challenge of rare samples with textual prompts to modulate visual features. However, they usually struggle to…

A representation is supposed universal if it encodes any element of the visual world (e.g., objects, scenes) in any configuration (e.g., scale, context). While not expecting pure universal representations, the goal in the literature is to…

Text spotting end-to-end methods have recently gained attention in the literature due to the benefits of jointly optimizing the text detection and recognition components. Existing methods usually have a distinct separation between the…

Scene Graph Generation (SGG) serves a comprehensive representation of the images for human understanding as well as visual understanding tasks. Due to the long tail bias problem of the object and predicate labels in the available annotated…

We propose and evaluate a neural point-based graphics method that can model semi-transparent scene parts. Similarly to its predecessor pipeline, ours uses point clouds to model proxy geometry, and augments each point with a neural…