Emos Yalp

https://openaccess.thecvf.com/content/CVPR2024/papers/Bai_BadCLIP_Trigger-Aware_Prompt_Learning_for_Backdoor_Attacks_on_CLIP_CVPR_2024_paper.pdfAbstractContrastive Vision-Language Pre-training known as CLIP has shown promising effectiveness in addressing downstream image recognition tasks. However recent works revealed that the CLIP model can be implanted with a downstream-oriented backdoor. On ..

https://openaccess.thecvf.com/content/CVPR2024/papers/Yuan_TEA_Test-time_Energy_Adaptation_CVPR_2024_paper.pdfAbstractTest Time Adaptation (TTA) aims to improve model generalizability when test data diverges from training distribution, with the distinct advantage of not requiring access to training data and processes, especially valuable in the context of pre-trained models. However, current TTA..

https://openaccess.thecvf.com/content/CVPR2024/papers/Choi_LTM_Lightweight_Textured_Mesh_Extraction_and_Refinement_of_Large_Unbounded_CVPR_2024_paper.pdfAbstractAdvancements in neural signed distance felds (SDFs) have enabled modeling 3D surface geometry from a set of 2D images of real-world scenes. Baking neural SDFs can extract explicit mesh with appearance baked into texture maps as neural fe..

https://openaccess.thecvf.com/content/CVPR2024/papers/Chiu_Brush2Prompt_Contextual_Prompt_Generator_for_Object_Inpainting_CVPR_2024_paper.pdfObject inpainting is a task that involves adding objects to real images and seamlessly compositing them. With the recent commercialization of products like Stable Diffusion and Generative Fill, inserting objects into images by using prompts has achieved imp..

https://openaccess.thecvf.com/content/CVPR2024/papers/Saha_Improved_Zero-Shot_Classification_by_Adapting_VLMs_with_Text_Descriptions_CVPR_2024_paper.pdfAbstractThe zero-shot performance of existing vision-language models $($VLMs$)$ such as CLIP is limited by the availability of large-scale, aligned image and text datasets in specific domains. In this work, we leverage two complementary sources o..

https://openaccess.thecvf.com/content/CVPR2024/papers/Ali-bey_BoQ_A_Place_is_Worth_a_Bag_of_Learnable_Queries_CVPR_2024_paper.pdfAbstractIn visual place recognition, accurately identifying and matching images of locations under varying environmental conditions and viewpoints remains a significant challenge. In this paper, we introduce a new technique, called Bag-of-Queries (BoQ), which learns a ..

https://openaccess.thecvf.com/content/CVPR2024/papers/Leng_HyperSDFusion_Bridging_Hierarchical_Structures_in_Language_and_Geometry_for_Enhanced_CVPR_2024_paper.pdfAbstract3D shape generation from text is a fundamental task in 3D representation learning. The text-shape pairs exhibit a hierarchical structure, where a general text like “chair” covers all 3D shapes of the chair, while more detailed ..

https://openaccess.thecvf.com/content/CVPR2024/papers/Li_Bridging_the_Synthetic-to-Authentic_Gap_Distortion-Guided_Unsupervised_Domain_Adaptation_for_Blind_CVPR_2024_paper.pdfAbstractThe annotation of blind image quality assessment (BIQA) is labor-intensive and time-consuming especially for authentic images. Training on synthetic data is expected to be beneficial but synthetically trained models..

https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136780420.pdfAbstractMost image denoising networks apply a single set of static convolutional kernels across the entire input image. This is sub-optimal for natural images, as they often consist of heterogeneous visual patterns. Dynamic convolution tries to address this issue by using per-pixel convolution kernels, but this greatly increas..

https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136750176.pdfAbstractImage-based volumetric humans using pixel-aligned features promise generalization to unseen poses and identities. Prior work leverages global spatial encodings and multi-view geometric consistency to reduce spatial ambiguity. However, global encodings often suffer from overfitting to the distribution of the training da..