9 papers
JEPA Guided Diffusion: Predictive Vision-Language Conditioning for Generative Traffic Forecasting
Trinh Tra Giang Nguyen, Thanh Nguyen Vo, Nguyen Hoai Thuong Bui +1
Accurate traffic forecasting requires both understanding scene dynamics and synthesizing realistic future observations. Recent diffusion-based video generation models produce visua…
Action-Aligned Retrieval with Pairwise Multimodal Reranking for Text-Based Person Anomaly Search
Thanh-Khoi Nguyen, Thanh-Nhan Vo, Trong-Thuan Nguyen +1
Text-based person anomaly search requires distinguishing individuals based on fine-grained, context-dependent behaviors rather than mere appearance. Existing methods struggle to ca…
TreeSoc: Tree-Structured Dynamic Reasoning and Tool Synergy for Soccer Video Understanding
Thanh-Nhan Vo, Thanh-Khoi Nguyen, Trong-Thuan Nguyen +2
Automated understanding of complex soccer scenarios from video remains a significant challenge for contemporary vision-language models (VLMs), which suffer from shallow cross-modal…
SAGA: Stable Acceleration Guidance for Autoregressive Video Generation
Thanh-Nhan Vo, Trong-Thuan Nguyen, Trung-Hoang Le +2
Autoregressive video diffusion enables efficient streaming and long-horizon video generation, but repeatedly reusing generated latents as causal context can amplify temporal errors…
SoccerNet 2026 Challenges Results
Anthony Cioppa, Silvio Giancola, Håkan Ardö +102
The SoccerNet 2026 Challenges constitute the sixth annual edition of the SoccerNet open benchmarking effort, dedicated to advancing computer vision research in sports video underst…
SimGraph: A Unified Framework for Scene Graph-Based Image Generation and Editing
Thanh-Nhan Vo, Trong-Thuan Nguyen, Tam V. Nguyen +1
Recent advancements in Generative Artificial Intelligence (GenAI) have significantly enhanced the capabilities of both image generation and editing. However, current approaches oft…
VENUS: Visual Editing with Noise Inversion Using Scene Graphs
Thanh-Nhan Vo, Trong-Thuan Nguyen, Tam V. Nguyen +1
State-of-the-art text-based image editing models often struggle to balance background preservation with semantic consistency, frequently resulting either in the synthesis of entire…
Toward Content-based Indexing and Retrieval of Head and Neck CT with Abscess Segmentation
Thao Thi Phuong Dao, Tan-Cong Nguyen, Trong-Le Do +13
Abscesses in the head and neck represent an acute infectious process that can potentially lead to sepsis or mortality if not diagnosed and managed promptly. Accurate detection and…
SATURN: Autoregressive Image Generation Guided by Scene Graphs
Thanh-Nhan Vo, Trong-Thuan Nguyen, Tam V. Nguyen +1
State-of-the-art text-to-image models excel at photorealistic rendering but often struggle to capture the layout and object relationships implied by complex prompts. Scene graphs p…