We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Our objective is to generate Audio Descriptions (ADs) for both movies and TV series in a training-free manner. We use the power of off-the-shelf Visual-Language Models (VLMs) and Large Language Models (LLMs), and develop visual and text prompting strategies for this task. Our contributions are three-fold: (i) We demonstrate that a VLM can successfully name and refer to characters if directly prompted with character information through visual indications without requiring any fine-tuning; (ii) A two-stage process is developed to generate ADs, with the first stage asking the VLM to comprehensively describe the video, followed by a second stage utilising a LLM to summarise dense textual information into one succinct AD sentence; (iii) A new dataset for TV audio description is formulated. Our approach, named AutoAD-Zero, demonstrates outstanding performance (even competitive with some models fine-tuned on ground truth ADs) in AD generation for both movies and TV series, achieving state-of-the-art CRITIC scores.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2407.15850")
get_code_for_paper("2407.15850")
have("2407.15850")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2407.15850.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2407.15850)
Connect an agent — have() is free.