Jaclyn Pytlarz

Lipisha Chaudhary, Trisha Mittal, Subhadra Gopalakrishnan et al.

Audio Descriptions (AD) are essential for making visual content accessible to individuals with visual impairments. Recent works have shown a promising step towards automating AD, but they have been limited to describing high-quality movie content using human-annotated ground truth AD in the process. In this work, we present an end-to-end pipeline, MCAD, that extends AD generation beyond movies to the domain of sports, with a focus on soccer games, without relying on ground truth AD. To address the absence of domain-specific AD datasets, we fine-tune a Video Large Language Model on publicly available movie AD datasets so that it learns the narrative structure and conventions of AD. During inference, MCAD incorporates multimodal contextual cues such as player identities, soccer events and actions, and commentary from the game. These cues, combined with input prompts to the fine-tuned VideoLLM, allow the system to produce complete AD text for each video segment. We further introduce a new evaluation metric, ARGE-AD, designed to accurately assess the quality of generated AD. ARGE-AD evaluates the generated AD for the presence of five characteristics: (i) usage of people's names, (ii) mention of actions and events, (iii) appropriate length of AD, (iv) absence of pronouns, and (v) overlap from commentary or subtitles. We present an in-depth analysis of our approach on both movie and soccer datasets. We also validate the use of this metric to quantitatively comment on the quality of generated AD using our metric across domains. Additionally, we contribute audio descriptions for 100 soccer game clips annotated by two AD experts.

Jin Huang, Subhadra Gopalakrishnan, Trisha Mittal et al.

Recent advancements in Artificial Intelligence have led to remarkable improvements in generating realistic human faces. While these advancements demonstrate significant progress in generative models, they also raise concerns about the potential misuse of these generated images. In this study, we investigate how humans perceive and distinguish between real and fake images. We designed a perceptual experiment using eye-tracking technology to analyze how individuals differentiate real faces from those generated by AI. Our analysis of StyleGAN-3 generated images reveals that participants can distinguish real from fake faces with an average accuracy of 76.80%. Additionally, we found that participants scrutinize images more closely when they suspect an image to be fake. We believe this study offers valuable insights into human perception of AI-generated media.

Divya Kothandaraman, Jaclyn Pytlarz

Memorization in large-scale text-to-image diffusion models poses significant security and intellectual property risks, enabling adversarial attribute extraction and the unauthorized reproduction of sensitive or proprietary features. While conventional dememorization techniques, such as regularization and data filtering, limit overfitting to specific training examples, they fail to systematically prevent the internalization of prohibited concept-level features. Simply discarding all images containing a sensitive feature wastes invaluable training data, necessitating a method for selective learning at the concept level. We introduce a gradient projection method designed to enforce a stringent requirement of concept-level feature exclusion. Our defense operates during backpropagation by systematically identifying and excising training signals aligned with embeddings of prohibited attributes. Specifically, we project each gradient update onto the orthogonal complement of the sensitive feature's embedding space, thereby zeroing out its influence on the model's weights. Our method integrates seamlessly into standard diffusion model training pipelines and complements existing defenses. We analyze our method against an adversary aiming for feature extraction. In extensive experiments, we demonstrate that our framework drastically reduces memorization while rigorously preserving generation quality and semantic fidelity. By reframing memorization control as selective learning, our approach establishes a new paradigm for IP-safe and privacy-preserving generative AI.

M. Kerem Aydin, Yi-Chun Hung, Jaclyn Pytlarz et al.

Hyperspectral cameras face harsh trade-offs between spatial, spectral, and temporal resolution in an inherently low-photon regime. Computational imaging systems break through these trade-offs with compressive sensing, but require complex optics and/or extensive compute. We present Spectrum from Defocus (SfD), a chromatic focal sweep method that recovers state-of-the-art hyperspectral images with a small system of off-the-shelf optics and < 1 second of compute. Our camera uses two lenses and a grayscale sensor to preserve nearly all incident light in a chromatically-aberrated focal stack. Our physics-based iterative algorithm efficiently demixes, deconvolves, and denoises the blurry grayscale focal stack into a sharp spectral image. The combination of photon efficiency, optical simplicity, and physical modeling makes SfD a promising solution for fast, compact, interpretable hyperspectral imaging.