News
CMAI in the European Conference of Computer Vision (12 papers and 1 workshop organisation)
Centre for Multimodal AI27 September 2024
7 papers from the Centre of Multimodal AI have been accepted and are to be presented in the main conference
- A Secure Image Watermarking Framework with Statistical Guarantees via Adversarial Attacks on Secret Key Networks. Feiyu Chen· Wei Lin · Ziquan Liu · Antoni Chan
- RAVE: Residual Vector Embedding for CLIP-Guided Backlit Image Enhancement. Tatiana Gaintseva · Martin Benning · Gregory Slabaugh. https://github.com/Atmyre/RAVE
- SHINE: Saliency-aware HIerarchical NEgative Ranking for Compositional Temporal Grounding. Zixu Cheng · Yujiang Pu · Shaogang Gong · Parisa Kordjamshidi · Yu Kong, https://github.com/zxccade/SHINE
- Few-Shot Image Generation by Conditional Relaxing Diffusion Inversion. Yu Cao · Shaogang Gong, https://yucao16.github.io/CRDI/
- RoGUENeRF: A Robust Geometry-Consistent Universal Enhancer for NeRF. Sibi Catley-Chandar · Richard Shaw · Gregory Slabaugh · Eduardo Pellitero
- CLIP-DPO: Vision-Language Models as a Source of Preference for Fixing Hallucinations in LVLMs, Yassine Ouali · Adrian Bulat · Brais Martinez · Georgios Tzimiropoulos
- Efficient Unsupervised Visual Representation Learning with Explicit Cluster Balancing. Ioannis Metaxas · Georgios Tzimiropoulos · Ioannis Patras. https://github.com/ManiadisG/ExCB
5 papers have been accepted and are to be presented in workshops
- Are CLIP features all you need for Universal Synthetic Image Origin Attribution? Dario Cioni, Christos Tzelepis, Lorenzo Seidenari, Ioannis Patras. At: Trust What You Learn Workshop. Best paper award, https://ciodar.github.io/UniversalAttribution/
- MM2Latent: Text-to-facial image generation and editing in GANs with multimodal assistance, Advances in Image Manipulation workshop (AIM) Workshop https://github.com/Open-Debin/MM2Latent
- Adaptive Multi-Modal Control of Digital Human Hand Synthesis using a Region-Aware Cycle Loss, Observing and Understanding Hands in Action (HANDS) Workshop, Qifan Fu · Xiaohang Yang · Muhammad Asad · Changjae Oh · Shanxin Yuan · Gregory Slabaugh
- Segmenting Object Affordances: Reproducibility and Sensitivity to Scale. At: 12th International Workshop on Assistive Computer Vision and Robotics. Tommaso Apicella · Alessio Xompero · Paolo Gastaldo · Andrea Cavallaro
- Adversarial Policy Generation in Automated Parking. At: Multimodal Perception and Comprehension of Corner Cases in Autonomous Driving. Alessandro Pighetti · Francesco Bellotti · Riccardo Berta · Andrea Cavallaro · Luca Lazzaroni · Changjae Oh
Workshop Organization
Updated by: Ioannis Patras