SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2310.07259 · 2023

Uncovering Hidden Connections: Iterative Search and Reasoning for Video-grounded Dialog

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 6 functions out of this paper's own repositories and ran 3 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
Hyu-Zhang/ISR canonical 3 of 6
FunctionStatusWhere it lives
attention Ran Hyu-Zhang/ISR/model/modules.py
pointer only (licence: NONE) · get_code("0cf22e1991ad4ef4")
clones Ran Hyu-Zhang/ISR/model/modules.py
pointer only (licence: NONE) · get_code("b1bec2c4b1c9b491")
get_median Ran Hyu-Zhang/ISR/process/statistic.py
pointer only (licence: NONE) · get_code("e8bef9401ec71c37")
beam_search_decode Not yet run Hyu-Zhang/ISR/model/decode.py
pointer only (licence: NONE) · get_code("89907e10d81267fc")
generate_response Not yet run Hyu-Zhang/ISR/generate.py
pointer only (licence: NONE) · get_code("b65d11d0d5341747")
make_model Not yet run Hyu-Zhang/ISR/model/mtn.py
pointer only (licence: NONE) · get_code("dbce9dd244c5dcd2")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

In contrast to conventional visual question answering, video-grounded dialog necessitates a profound understanding of both dialog history and video content for accurate response generation. Despite commendable progress made by existing approaches, they still face the challenges of incrementally understanding complex dialog history and assimilating video information. In response to these challenges, we present an iterative search and reasoning framework, which consists of a textual encoder, a visual encoder, and a generator. Specifically, we devise a path search and aggregation strategy in the textual encoder, mining core cues from dialog history that are pivotal to understanding the posed questions. Concurrently, our visual encoder harnesses an iterative reasoning network to extract and emphasize critical visual markers from videos, enhancing the depth of visual comprehension. Finally, we utilize the pre-trained GPT-2 model as our answer generator to decode the mined hidden clues into coherent and contextualized answers. Extensive experiments on three public datasets demonstrate the effectiveness and generalizability of our proposed framework.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2310.07259")
get_code_for_paper("2310.07259")
have("2310.07259")

Connect an agent — have() is free.