Related papers: RelTransformer: A Transformer-Based Long-Tail Visu…
The objective of this work is to improve the accuracy of building demand forecasting. This is a more challenging task than grid level forecasting. For the said purpose, we develop a new technique called recurrent transform learning (RTL).…
We propose a transformer-based neural network architecture for multi-object 3D reconstruction from RGB videos. It relies on two alternative ways to represent its knowledge: as a global 3D grid of features and an array of view-specific 2D…
Video Visual Relation Detection (VidVRD), has received significant attention of our community over recent years. In this paper, we apply the state-of-the-art video object tracklet detection pipeline MEGA and deepSORT to generate tracklet…
Understanding and reasoning over long videos pose significant challenges for large video language models (LVLMs) due to the difficulty in processing intensive video tokens beyond context window and retaining long-term sequential…
Relationships among objects play a crucial role in image understanding. Despite the great success of deep learning techniques in recognizing individual objects, reasoning about the relationships among objects remains a challenging task.…
Video Scene Graph Generation aims to obtain structured semantic representations of objects and their relationships in videos for high-level understanding. However, existing methods still have limitations in handling long-tail distributions.…
Generalizable neural surface reconstruction techniques have attracted great attention in recent years. However, they encounter limitations of low confidence depth distribution and inaccurate surface reasoning due to the oversimplified…
Visual Relationship Detection (VRD) impels a computer vision model to 'see' beyond an individual object instance and 'understand' how different objects in a scene are related. The traditional way of VRD is first to detect objects in an…
The relations expressed in user queries are vital for cross-modal information retrieval. Relation-focused cross-modal retrieval aims to retrieve information that corresponds to these relations, enabling effective retrieval across different…
The simultaneous recognition of multiple objects in one image remains a challenging task, spanning multiple events in the recognition field such as various object scales, inconsistent appearances, and confused inter-class relationships.…
The crux of Referring Video Object Segmentation (RVOS) lies in modeling dense text-video relations to associate abstract linguistic concepts with dynamic visual contents at pixel-level. Current RVOS methods typically use vision and language…
We propose a Vision-Language Transformer (VLT) framework for referring segmentation to facilitate deep interactions among multi-modal information and enhance the holistic understanding to vision-language features. There are different ways…
Recurrent Neural Networks have long been the dominating choice for sequence modeling. However, it severely suffers from two issues: impotent in capturing very long-term dependencies and unable to parallelize the sequential computation…
In the real world, medical datasets often exhibit a long-tailed data distribution (i.e., a few classes occupy most of the data, while most classes have rarely few samples), which results in a challenging imbalance learning scenario. For…
In order to answer semantically-complicated questions about an image, a Visual Question Answering (VQA) model needs to fully understand the visual scene in the image, especially the interactive dynamics between different objects. We propose…
Multimodal Large Language Models (MLLMs) show promise for image-based regression tasks, but current approaches face key limitations. Recent methods fine-tune MLLMs using preset output vocabularies and generic task-level prompts (e.g., "How…
Visual relations, such as "person ride bike" and "bike next to car", offer a comprehensive scene understanding of an image, and have already shown their great utility in connecting computer vision and natural language. However, due to the…
Transformers have achieved success in both language and vision domains. However, it is prohibitively expensive to scale them to long sequences such as long documents or high-resolution images, because self-attention mechanism has quadratic…
Parameter-efficient fine-tuning for pre-trained Vision Transformers aims to adeptly tailor a model to downstream tasks by learning a minimal set of new adaptation parameters while preserving the frozen majority of pre-trained parameters.…
Attention mechanisms have been very popular in deep neural networks, where the Transformer architecture has achieved great success in not only natural language processing but also visual recognition applications. Recently, a new Transformer…