相关论文: ViscoNet: Bridging and Harmonizing Visual and Text…
Consistency Training (CT) has recently emerged as a strong alternative to diffusion models for image generation. However, non-distillation CT often suffers from high variance and instability, motivating ongoing research into its training…
Diffusion-based virtual try-on methods achieve photorealistic synthesis through cross-attention mechanisms that transfer garment features to target body regions. However, these approaches rely on implicit learning of spatial…
Blending visual and textual concepts into a new visual concept is a unique and powerful trait of human beings that can fuel creativity. However, in practice, cross-modal conceptual blending for humans is prone to cognitive biases, like…
The reconfigurable intelligent surface (RIS) is a promising technology for next-generation wireless communication. It comprises many passive antennas, which reflect signals from the transmitter to the receiver with adjusted phases without…
This paper presents a novel design methodology for architecting a light-weight and faster DNN architecture for vision applications. The effectiveness of the architecture is demonstrated on Color-Constancy use case an inherent block in…
Text-guided image-to-video (I2V) generation aims to generate a coherent video that preserves the identity of the input image and semantically aligns with the input prompt. Existing methods typically augment pretrained text-to-video (T2V)…
This paper presents ViTOC (Vision Transformer and Object-aware Captioner), a novel vision-language model for image captioning that addresses the challenges of accuracy and diversity in generated descriptions. Unlike conventional approaches,…
Ultra-low bitrate image compression is a challenging and demanding topic. With the development of Large Multimodal Models (LMMs), a Cross Modality Compression (CMC) paradigm of Image-Text-Image has emerged. Compared with traditional codecs,…
Deploying high-performance vision transformer (ViT) models on ubiquitous Internet of Things (IoT) devices to provide high-quality vision services will revolutionize the way we live, work, and interact with the world. Due to the…
Document understanding and GUI interaction are among the highest-value applications of Vision-Language Models (VLMs), yet they impose exceptionally heavy computational burden: fine-grained text and small UI elements demand high-resolution…
Collaborative perception is vital for autonomous driving yet remains constrained by tight communication budgets. Earlier work reduced bandwidth by compressing full feature maps with fixed-rate encoders, which adapts poorly to a changing…
A major challenge in rare animal image classification is the scarcity of data, as many species usually have only a small number of labeled samples. To address this challenge, we designed a hybrid deep-learning framework comprising a novel…
Recent vision-language models have achieved tremendous advances. However, their computational costs are also escalating dramatically, making model acceleration exceedingly critical. To pursue more efficient vision-language Transformers,…
Video super-resolution (VSR) is a task that aims to reconstruct high-resolution (HR) frames from the low-resolution (LR) reference frame and multiple neighboring frames. The vital operation is to utilize the relative misaligned frames for…
It is well known that featuremap attention and multi-path representation are important for visual recognition. In this paper, we present a modularized architecture, which applies the channel-wise attention on different network branches to…
Cross-subject brain-to-visual decoding remains a core challenge in brain-computer interfaces due to severe inter-individual variability that induces systematic subject-specific functional misalignment. To address this issue, we propose…
We introduce MVControl, a novel neural network architecture that enhances existing pre-trained multi-view 2D diffusion models by incorporating additional input conditions, e.g. edge maps. Our approach enables the generation of controllable…
Document image enhancement is a fundamental and important stage for attaining the best performance in any document analysis assignment because there are many degradation situations that could harm document images, making it more difficult…
Recently, diffusion models have been proven to perform remarkably well in text-to-image synthesis tasks in a number of studies, immediately presenting new study opportunities for image generation. Google's Imagen follows this research trend…
Unified models aim to support both understanding and generation by encoding images into discrete tokens and processing them alongside text within a single autoregressive framework. This unified design offers architectural simplicity and…