What You See is What You Ask: Evaluating Audio Descriptions

Audio descriptions (ADs) narrate important visual details in movies, enabling Blind and Low Vision (BLV) users to understand narratives and appreciate visual details. Existing works in automatic AD generation mostly focus on few-second trimmed clips, and evaluate them by comparing against a single ground-truth reference AD. However, writing ADs is inherently subjective. Through alignment and analysis of two independent AD tracks for the same movies, we quantify the subjectivity in when and whether to describe, and what and how to highlight. Thus, we show that working with trimmed clips is inadequate. We propose ADQA, a QA benchmark that evaluates ADs at the level of few-minute long, coherent video segments, testing whether they would help BLV users understand the story and appreciate visual details. ADQA features visual appreciation (VA) questions about visual facts and narrative understanding (NU) questions based on the plot. Through ADQA, we show that current AD generation methods lag far behind human-authored ADs. We conclude with several recommendations for future work and introduce a public leaderboard for benchmarking.

Shot-by-Shot: Film-Grammar-Aware Training-Free Audio Description Generation

Our objective is the automatic generation of Audio Descriptions (ADs) for edited video material, such as movies and TV series. To achieve this, we propose a two-stage framework that leverages "shots" as the fundamental units of video understanding. This includes extending temporal context to neighbouring shots and incorporating film grammar devices, such as shot scales and thread structures, to guide AD generation. Our method is compatible with both open-source and proprietary Visual-Language Models (VLMs), integrating expert knowledge from add-on modules without requiring additional training of the VLMs. We achieve state-of-the-art performance among all prior training-free approaches and even surpass fine-tuned methods on several benchmarks. To evaluate the quality of predicted ADs, we introduce a new evaluation measure -- an action score -- specifically targeted to assessing this important aspect of AD. Additionally, we propose a novel evaluation protocol that treats automatic frameworks as AD generation assistants and asks them to generate multiple candidate ADs for selection.

Eye vs. AI: Human Gaze and Model Attention in Video Memorability

Understanding the factors that determine video memorability has important applications in areas such as educational technology and advertising. Towards this goal, we investigate the semantic and temporal attention mechanisms underlying video memorability. We propose a Transformer-based model with spatio-temporal attention that matches SoTA performance on video memorability prediction on a large naturalistic video dataset. More importantly, the self-attention patterns show us where the model looks to predict memorability. We compare model attention against human gaze fixation density maps collected through a small-scale eye-tracking experiment where humans perform a video memory task. Quantitative saliency metrics show that the model attention and human gaze follow similar patterns. Furthermore, while panoptic segmentation confirms that the model and humans attend more to thing classes, stuff classes that receive increased/decreased attention tend to have higher memorability scores. We also observe that the model assigns greater importance to the initial frames, mimicking temporal attention patterns found in humans.