相关论文: MoVie: Revisiting Modulated Convolutions for Visua…

Visual QA is a pivotal challenge for higher-level reasoning, requiring understanding language, vision, and relationships between many objects in a scene. Although datasets like CLEVR are designed to be unsolvable without such complex…

Efficient processing of high-res video streams is safety-critical for many robotics applications such as autonomous driving. To maintain real-time performance, many practical systems downsample the video stream. But this can hurt downstream…

One of the most intriguing features of the Visual Question Answering (VQA) challenge is the unpredictability of the questions. Extracting the information required to answer them demands a variety of image operations from detection and…

Visual imagery does not consist of solitary objects, but instead reflects the composition of a multitude of fluid concepts. While there have been great advances in visual representation learning, such advances have focused on building…

We propose the use of dilated filters to construct an aggregation module in a multicolumn convolutional neural network for perspective-free counting. Counting is a common problem in computer vision (e.g. traffic on the street or pedestrians…

Vector quantization (VQ) transforms continuous image features into discrete representations, providing compressed, tokenized inputs for generative models. However, VQ-based frameworks suffer from several issues, such as non-smooth latent…

This paper presents CountEx, a discriminative visual counting framework designed to address a key limitation of existing prompt-based methods: the inability to explicitly exclude visually similar distractors. While current approaches allow…

Despite significant success in Visual Question Answering (VQA), VQA models have been shown to be notoriously brittle to linguistic variations in the questions. Due to deficiencies in models and datasets, today's models often rely on…

Light-weight convolutional neural networks (CNNs) are the de-facto for mobile vision tasks. Their spatial inductive biases allow them to learn representations with fewer parameters across different vision tasks. However, these networks are…

Typical active learning strategies are designed for tasks, such as classification, with the assumption that the output space is mutually exclusive. The assumption that these tasks always have exactly one correct answer has resulted in the…

Vision-Language Models (VLMs) excel at reasoning in linguistic space but struggle with perceptual understanding that requires dense visual perception, e.g., spatial reasoning and geometric awareness. This limitation stems from the fact that…

As convolution has empowered many smart applications, dynamic convolution further equips it with the ability to adapt to diverse inputs. However, the static and dynamic convolutions are either layout-agnostic or computation-heavy, making it…

Visual question answering (VQA) has witnessed great progress since May, 2015 as a classic problem unifying visual and textual data into a system. Many enlightening VQA works explore deep into the image and question encodings and fusing…

We launch EVA, a vision-centric foundation model to explore the limits of visual representation at scale using only publicly accessible data. EVA is a vanilla ViT pre-trained to reconstruct the masked out image-text aligned vision features…

We present a novel unsupervised feature representation learning method, Visual Commonsense Region-based Convolutional Neural Network (VC R-CNN), to serve as an improved visual region encoder for high-level tasks such as captioning and VQA.…

The synergy of long-range dependencies from transformers and local representations of image content from convolutional neural networks (CNNs) has led to advanced architectures and increased performance for various medical image analysis…

Visual question answering (VQA) refers to the problem where, given an image and a natural language question about the image, a correct natural language answer has to be generated. A VQA model has to demonstrate both the visual understanding…

Visual Programming (VP) has emerged as a powerful framework for Visual Question Answering (VQA). By generating and executing bespoke code for each question, these methods demonstrate impressive compositional and reasoning capabilities,…

A multi-view image sequence provides a much richer capacity for object recognition than from a single image. However, most existing solutions to multi-view recognition typically adopt hand-crafted, model-based geometric methods, which do…

Visual Question Answering (VQA) requires models to identify the correct answer options based on both visual and textual evidence. Recent Mixture-of-Experts (MoE) methods improve option reasoning by grouping similar concepts or routing based…