8 citations · 31 across the 40 of their papers we have counts for
15 papers · 1 filter
Is Nano Banana Pro a Low-Level Vision All-Rounder? A Comprehensive Evaluation on 14 Tasks and 40 Datasets
Jialong Zuo, Haoyou Deng, Hanyu Zhou +10
The rapid evolution of text-to-image generation models has revolutionized visual content creation. While commercial products like Nano Banana Pro have garnered significant attentio…
HBridge: H-Shape Bridging of Heterogeneous Experts for Unified Multimodal Understanding and Generation
Xiang Wang, Zhifei Zhang, He Zhang +11
Recent unified models integrate understanding experts (e.g., LLMs) with generative experts (e.g., diffusion models), achieving strong multimodal performance. However, recent advanc…
Learning to Tell Apart: Weakly Supervised Video Anomaly Detection via Disentangled Semantic Alignment
Wenti Yin, Huaxin Zhang, Xiang Wang +7
Recent advancements in weakly-supervised video anomaly detection have achieved remarkable performance by applying the multiple instance learning paradigm based on multimodal founda…
Towards Reliable and Holistic Visual In-Context Learning Prompt Selection
Wenxiao Wu, Jing-Hao Xue, Chengming Xu +5
Visual In-Context Learning (VICL) has emerged as a prominent approach for adapting visual foundation models to novel tasks, by effectively exploiting contextual information embedde…
VideoLucy: Deep Memory Backtracking for Long Video Understanding
Jialong Zuo, Yongtai Deng, Lingdong Kong +7
Recent studies have shown that agent-based systems leveraging large language models (LLMs) for key information retrieval and integration have emerged as a promising approach for lo…
High-resolution Photo Enhancement in Real-time: A Laplacian Pyramid Network
Feng Zhang, Haoyou Deng, Zhiqiang Li +8
Photo enhancement plays a crucial role in augmenting the visual aesthetics of a photograph. In recent years, photo enhancement methods have either focused on enhancement performanc…
Partial Forward Blocking: A Novel Data Pruning Paradigm for Lossless Training Acceleration
Dongyue Wu, Zilin Guo, Jialong Zuo +2
The ever-growing size of training datasets enhances the generalization capability of modern machine learning models but also incurs exorbitant computational costs. Existing data pr…
Learning Unpaired Image Dehazing with Physics-based Rehazy Generation
Haoyou Deng, Zhiqiang Li, Feng Zhang +6
Overfitting to synthetic training pairs remains a critical challenge in image dehazing, leading to poor generalization capability to real-world scenarios. To address this issue, ex…
ReID5o: Achieving Omni Multi-modal Person Re-identification in a Single Model
Jialong Zuo, Yongtai Deng, Mengdan Tan +5
In real-word scenarios, person re-identification (ReID) expects to identify a person-of-interest via the descriptive query, regardless of whether the query is a single modality or…
MP-Mat: A 3D-and-Instance-Aware Human Matting and Editing Framework with Multiplane Representation
Siyi Jiao, Wenzheng Zeng, Yerong Li +4
Human instance matting aims to estimate an alpha matte for each human instance in an image, which is challenging as it easily fails in complex cases requiring disentangling mingled…
UniAnimate-DiT: Human Image Animation with Large-Scale Video Diffusion Transformer
Xiang Wang, Shiwei Zhang, Longxiang Tang +4
This report presents UniAnimate-DiT, an advanced project that leverages the cutting-edge and powerful capabilities of the open-source Wan2.1 model for consistent human image animat…
Taming Consistency Distillation for Accelerated Human Image Animation
Xiang Wang, Shiwei Zhang, Hangjie Yuan +5
Recent advancements in human image animation have been propelled by video diffusion models, yet their reliance on numerous iterative denoising steps results in high inference costs…
FedPCA: Noise-Robust Fair Federated Learning via Performance-Capacity Analysis
Nannan Wu, Zengqiang Yan, Nong Sang +2
Training a model that effectively handles both common and rare data-i.e., achieving performance fairness-is crucial in federated learning (FL). While existing fair FL methods have…
Object-Aware Video Matting with Cross-Frame Guidance
Huayu Zhang, Dongyue Wu, Yuanjie Shao +2
Recently, trimap-free methods have drawn increasing attention in human video matting due to their promising performance. Nevertheless, these methods still suffer from the lack of d…
CTR-Driven Advertising Image Generation with Multimodal Large Language Models
Xingye Chen, Wei Feng, Zhenbang Du +16
In web data, advertising images are crucial for capturing user attention and improving advertising effectiveness. Most existing methods generate background for products primarily f…