NSTL国家科技图书文献中心

1. Evaluating Text-to-Visual Generation with Image-to-Text Generation NSTL国家科技图书文献中心

Zhiqiu Lin | Deepak Pathak ... - 《Computer Vision - ECCV 2024,Part IX》 - European Conference on Computer Vision - 2025, - 366～384 - 共19页

摘要：Despite significant progress in generative AI | , comprehensive evaluation remains challenging because of the | lack of effective metrics and standardized benchmarks | . For instance, the widely-used CLIP-Score measures | the alignment between a (generated) image and text

关键词： Vision-Language models | Visio-Linguistic compositionality | Evaluation of generative models

2. Unclonable Cryptography with Unbounded Collusions and Impossibility of Hyperefficient Shadow Tomography NSTL国家科技图书文献中心

Alper Cakan | Vipul Goyal - 《Theory of Cryptography,Part III》 - Theory of Cryptography Conference - 2025, - 225～256 - 共32页

摘要：Quantum no-cloning theorem gives rise to the | intriguing possibility of quantum copy protection where we | encode a program or functionality in a quantum state | such that a user in possession of k copies cannot | create k + 1 copies, for any k. Introduced by Aaronson

关键词： Quantum cryptography | Unclonable cryptography | Shadow tomography | Copy protection

3. OmniACT: A Dataset and Benchmark for Enabling Multimodal Generalist Autonomous Agents for Desktop and Web NSTL国家科技图书文献中心

Raghav Kapoor | Yash Parag Butala ... - 《Computer Vision - ECCV 2024,Part LXVIII》 - European Conference on Computer Vision - 2025, - 161～178 - 共18页

摘要：For decades, human-computer interaction has | fundamentally been manual. Even today, almost all productive | work done on the computer necessitates human input at | every step. Autonomous virtual agents represent an | exciting step in automating many of these menial tasks

关键词： Generalist agent | Multimodal machine learning | Dataset and benchmark | Vision language understanding | UI grounding | Human-computer interaction

4. The INTENT Game: An Interactive Tool for Empathy in Neurotypicals NSTL国家科技图书文献中心

Varun Girdhar | Chao-Yang Tseng ... - 《Serious Games》 - Joint International Conference on Serious Games - 2025, - 433～439 - 共7页

摘要：This paper outlines the design and development | of a browser-based game for neurotypicals to gain | better understanding and empathy towards autistic | people in the workplace. The game will be added to an | arsenal of tools used by researchers planning to teach

关键词： Serious game | Transformational game | Autism spectrum disorder

5. FAMOUS: High-Fidelity Monocular 3D Human Digitization Using View Synthesis NSTL国家科技图书文献中心

Vishnu Mani Hema | Shubhra Aich ... - 《Computer Vision - ECCV 2024,Part LXXXII》 - European Conference on Computer Vision - 2025, - 57～73 - 共17页

摘要：The advancement in deep implicit modeling and | articulated models has significantly enhanced the process of | digitizing human figures in 3D from just a single image | . While state-of-the-art methods have greatly improved | geometric precision, the challenge of accurately inferring

关键词： Human digitization | 2D prior | Fashion dataset

6. Spectral Subsurface Scattering for Material Classification NSTL国家科技图书文献中心

Haejoon Lee | Aswin C. Sankaranara... - 《Computer Vision - ECCV 2024,Part V》 - European Conference on Computer Vision - 2025, - 108～124 - 共17页

摘要：This study advances material classification | using Spectral Sub-Surface Scattering (S~4 | ) measurements. While spectrum and subsurface scattering | measurements have individually been used in material | classification, we argue that the strong spectral dependence of

关键词： Spectral subsurface scattering | Material classification

7. Adaptive Human Trajectory Prediction via Latent Corridors NSTL国家科技图书文献中心

Neerja Thakkar | Karttikeya Mangalam ... - 《Computer Vision - ECCV 2024,Part XXXVIII》 - European Conference on Computer Vision - 2025, - 297～314 - 共18页

摘要：Human trajectory prediction is typically posed | as a zero-shot generalization problem: a predictor | is learnt on a dataset of human motion in training | scenes, and then deployed on unseen test scenes. While | this paradigm has yielded tremendous progress, it

关键词： Human trajectory prediction | Adaptation | Test-time training | Image prompt tuning

8. UpFusion: Novel View Diffusion from Unposed Sparse View Observations NSTL国家科技图书文献中心

Bharath Raj Nagoor K... | Hsin-Ying Lee ... - 《Computer Vision - ECCV 2024,Part LXXVI》 - European Conference on Computer Vision - 2025, - 179～195 - 共17页

摘要：We propose UpFusion, a system that can perform | novel view synthesis and infer 3D representations for | generic objects given a sparse set of reference images | without corresponding pose information. Current sparse | -view 3D inference methods typically rely on camera

关键词： Sparse-view 3D reconstruction | Novel-view synthesis | 3D generation

9. Enhanced Uncertainty Estimation in Ultrasound Image Segmentation with MSU-Net NSTL国家科技图书文献中心

Rohini Banerjee | Cecilia G. Morales ... - 《Simplifying Medical Ultrasound》 - International Workshop on Advances in Simplifying Medical Ultrasound | International Conference on Medical Image Computing and Computer Assisted Intervention - 2025, - 143～153 - 共11页

摘要：Efficient intravascular access in trauma and | critical care significantly impacts patient outcomes | . However, the availability of skilled medical personnel | in austere environments is often limited. Despite | advances in autonomous needle insertion, inaccuracies in

关键词： Uncertainty quantification · ultrasound image segmentation | Trustworthy and interpretable medical AI

10. Situated Instruction Following NSTL国家科技图书文献中心

So Yeon Min | Xavi Puig ... - 《Computer Vision - ECCV 2024,Part LXI》 - European Conference on Computer Vision - 2025, - 202～228 - 共27页

摘要：Language is never spoken in a vacuum. It is | expressed, comprehended, and contextualized within the | holistic backdrop of the speaker's history, actions, and | environment. Since humans are used to communicating | efficiently with situated language, the practicality of

摘要：Despite significant progress in generative AI | , comprehensive evaluation remains challenging because of the | lack of effective metrics and standardized benchmarks | . For instance, the widely-used CLIP-Score measures | the alignment between a (generated) image and text

关键词： Vision-Language models | Visio-Linguistic compositionality | Evaluation of generative models

摘要：Quantum no-cloning theorem gives rise to the | intriguing possibility of quantum copy protection where we | encode a program or functionality in a quantum state | such that a user in possession of k copies cannot | create k + 1 copies, for any k. Introduced by Aaronson

关键词： Quantum cryptography | Unclonable cryptography | Shadow tomography | Copy protection

摘要：For decades, human-computer interaction has | fundamentally been manual. Even today, almost all productive | work done on the computer necessitates human input at | every step. Autonomous virtual agents represent an | exciting step in automating many of these menial tasks

关键词： Generalist agent | Multimodal machine learning | Dataset and benchmark | Vision language understanding | UI grounding | Human-computer interaction

摘要：This paper outlines the design and development | of a browser-based game for neurotypicals to gain | better understanding and empathy towards autistic | people in the workplace. The game will be added to an | arsenal of tools used by researchers planning to teach

关键词： Serious game | Transformational game | Autism spectrum disorder

摘要：The advancement in deep implicit modeling and | articulated models has significantly enhanced the process of | digitizing human figures in 3D from just a single image | . While state-of-the-art methods have greatly improved | geometric precision, the challenge of accurately inferring

关键词： Human digitization | 2D prior | Fashion dataset

摘要：This study advances material classification | using Spectral Sub-Surface Scattering (S~4 | ) measurements. While spectrum and subsurface scattering | measurements have individually been used in material | classification, we argue that the strong spectral dependence of

关键词： Spectral subsurface scattering | Material classification

摘要：Human trajectory prediction is typically posed | as a zero-shot generalization problem: a predictor | is learnt on a dataset of human motion in training | scenes, and then deployed on unseen test scenes. While | this paradigm has yielded tremendous progress, it

关键词： Human trajectory prediction | Adaptation | Test-time training | Image prompt tuning

摘要：We propose UpFusion, a system that can perform | novel view synthesis and infer 3D representations for | generic objects given a sparse set of reference images | without corresponding pose information. Current sparse | -view 3D inference methods typically rely on camera

关键词： Sparse-view 3D reconstruction | Novel-view synthesis | 3D generation

摘要：Efficient intravascular access in trauma and | critical care significantly impacts patient outcomes | . However, the availability of skilled medical personnel | in austere environments is often limited. Despite | advances in autonomous needle insertion, inaccuracies in

关键词： Uncertainty quantification · ultrasound image segmentation | Trustworthy and interpretable medical AI

摘要：Language is never spoken in a vacuum. It is | expressed, comprehended, and contextualized within the | holistic backdrop of the speaker's history, actions, and | environment. Since humans are used to communicating | efficiently with situated language, the practicality of

关键词： Instruction following | Embodied AI | LLM agent

4008-161-200 800-990-8900

国家科技图书文献中心