8 citations · 33 across the 39 of their papers we have counts for
40 papers · 1 filter
Tether the Subject, Release the Scene: Query-Aware Memory Routing for Long-Horizon Autoregressive Video Generation
Chen Li, Peng Zhang, Hanyu Zhou +5
Streaming autoregressive video models generate long videos chunk by chunk, using historical memory to maintain consistency. Existing methods typically expose subject and scene quer…
Aggregating Visual Information with Optimal Transport for VideoLM Token Compression
Wenti Yin, Xiaotian Han, Junyuan Shang +5
Video language models process videos as dense visual-token sequences with substantial representational redundancy. Compressing these sequences is therefore essential for reducing t…
Beyond Hazard Resemblance: Contrastive Event Adjudication for Training-Free Video Anomaly Detection
Wenti Yin, Xiang Wang, Huaxin Zhang +4
Video anomaly detection (VAD) aims to identify and temporally localize abnormal events in videos. Supervised methods learn anomaly decision boundaries from target-domain annotation…
Clarity Contrast and Similarity Selection for Multi-Focus Image Fusion
Yicheng Zhang, Haoyou Deng, Zhiqiang Li +3
Multi-focus image fusion (MFIF) aims to generate an all-in-focus image from multiple images of the same scene focused at different regions. Most existing deep learning-based method…
Achieving Text-based Person Retrieval with Any Granularity
Jialong Zuo, Hanyu Zhou, Dongyue Wu +5
Text-based person retrieval faces a critical but under-explored challenge: the inherent uncertainty of query granularity in real-world scenarios. This paper introduces a new paradi…
FilmWorld: Agentic Novel-to-Film Generation through Dynamic Cinematic World Modeling
Jialong Zuo, Haotong Zuo, Shiwei Zhang +5
Translating novels into films poses a grand challenge for generative artificial intelligence, requiring conversion of abstract literary prose into long-form, multi-scene visual nar…
Focusing on What Matters: Saliency-Harnessing Accurate Routing for Diffusion MoE
Haoyou Deng, Keyu Yan, Chaojie Mao +4
Mixture-of-Experts (MoE) architectures have emerged as a powerful paradigm for scaling diffusion models in visual generation. Recent advancements have focused on adaptively allocat…
INTACT: Ego-Guided Typed Sparse Evidence Retrieval for Heterogeneous Collaborative Perception
Chen Li, Shengrong Yuan, Jialong Zuo +3
Collaborative perception extends the perceptual range of autonomous vehicles by sharing information across agents, but heterogeneous sensors and perception models make intermediate…
Is Your Driving World Model an All-Around Player?
Lingdong Kong, Ao Liang, Tianyi Yan +20
Today's driving world models can generate remarkably realistic dash-cam videos, yet no single model excels universally. Some generate photorealistic textures but violate basic phys…
DenseGRPO: From Sparse to Dense Reward for Flow Matching Model Alignment
Haoyou Deng, Keyu Yan, Chaojie Mao +4
Recent GRPO-based approaches built on flow matching models have shown remarkable improvements in human preference alignment for text-to-image generation. Nevertheless, they still s…
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…
WorldLens: Full-Spectrum Evaluations of Driving World Models in Real World
Ao Liang, Lingdong Kong, Tianyi Yan +19
Generative world models are reshaping embodied AI, enabling agents to synthesize realistic 4D driving environments that look convincing but often fail physically or behaviorally. D…
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…
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…
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…
Holmes-VAU: Towards Long-term Video Anomaly Understanding at Any Granularity
Huaxin Zhang, Xiaohao Xu, Xiang Wang +6
How can we enable models to comprehend video anomalies occurring over varying temporal scales and contexts? Traditional Video Anomaly Understanding (VAU) methods focus on frame-lev…