Related papers: CATs: Cost Aggregation Transformers for Visual Cor…

Vision transformers in vision-language models typically use the same amount of compute for every image, regardless of whether it is simple or complex. We propose ICAR (Image Complexity-Aware Retrieval), an adaptive computation approach that…

Visual Transformers (VTs) are emerging as an architectural paradigm alternative to Convolutional networks (CNNs). Differently from CNNs, VTs can capture global relations between image elements and they potentially have a larger…

As the most critical components in a sentence, subject, predicate and object require special attention in the video captioning task. To implement this idea, we design a novel framework, named COllaborative three-Stream Transformers (COST),…

As the state-of-the-art machine learning methods in many fields rely on larger datasets, storing datasets and training models on them become significantly more expensive. This paper proposes a training set synthesis technique for…

Deep clustering - joint representation learning and latent space clustering - is a well studied problem especially in computer vision and text processing under the deep learning framework. While the representation learning is generally…

Unsupervised image translation, which aims in translating two independent sets of images, is challenging in discovering the correct correspondences without paired data. Existing works build upon Generative Adversarial Network (GAN) such…

We propose a novel ECGAN for the challenging semantic image synthesis task. Although considerable improvements have been achieved by the community in the recent period, the quality of synthesized images is far from satisfactory due to three…

Tracking multiple people across multiple cameras is an open problem. It is typically divided into two tasks: (i) single-camera tracking (SCT) - identify trajectories in the same scene, and (ii) inter-camera tracking (ICT) - identify…

Diffusion models have revolutionized generative tasks, especially in the domain of text-to-image synthesis; however, their iterative denoising process demands substantial computational resources. In this paper, we present a novel…

We introduce a self-attending task generative adversarial network (SATGAN) and apply it to the problem of augmenting synthetic high contrast scientific imagery of resident space objects with realistic noise patterns and sensor…

Crowd counting is a challenging problem due to the scene complexity and scale variation. Although deep learning has achieved great improvement in crowd counting, scene complexity affects the judgement of these methods and they usually…

Convolutional neural networks (CNNs) have become the dominant neural network architecture for solving visual processing tasks. One of the major obstacles hindering the ubiquitous use of CNNs for inference is their relatively high memory…

Due to the rapid growth of Electrical Capacitance Tomography (ECT) applications in several industrial fields, there is a crucial need for developing high quality, yet fast, methodologies of image reconstruction from raw capacitance…

This paper proposes a novel deep learning-based video object matting method that can achieve temporally coherent matting results. Its key component is an attention-based temporal aggregation module that maximizes image matting networks'…

We propose In-Context Translation (ICT), a general learning framework to unify visual recognition (e.g., semantic segmentation), low-level image processing (e.g., denoising), and conditional image generation (e.g., edge-to-image synthesis).…

We present ASSET, a neural architecture for automatically modifying an input high-resolution image according to a user's edits on its semantic segmentation map. Our architecture is based on a transformer with a novel attention mechanism.…

One of the key factors in language productivity and human cognition is the ability of systematic compositionality, which refers to understanding composed unseen examples of seen primitives. However, recent evidence reveals that the…

The significant progress on Generative Adversarial Networks (GANs) has facilitated realistic single-object image generation based on language input. However, complex-scene generation (with various interactions among multiple objects) still…

Text-to-image synthesis has recently seen significant progress thanks to large pretrained language models, large-scale training data, and the introduction of scalable model families such as diffusion and autoregressive models. However, the…

Unsupervised fine-grained class clustering is a practical yet challenging task due to the difficulty of feature representations learning of subtle object details. We introduce C3-GAN, a method that leverages the categorical inference power…