Subarna Tripathi, Kyle Min, Sourya Roy, Tanaya Guha, Somdeb Majumdar
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.
Active speaker detection (ASD) in videos with multiple speakers is a challenging task as it requires learning effective audiovisual features and spatial-temporal correlations over long temporal windows. In this paper, we present SPELL, a novel spatial-temporal graph learning framework that can solve complex tasks such as ASD. To this end, each person in a video frame is first encoded in a unique node for that frame. Nodes corresponding to a single person across frames are connected to encode their temporal dynamics. Nodes within a frame are also connected to encode inter-person relationships. Thus, SPELL reduces ASD to a node classification task. Importantly, SPELL is able to reason over long temporal contexts for all nodes without relying on computationally expensive fully connected graph neural networks. Through extensive experiments on the AVA-ActiveSpeaker dataset, we demonstrate that learning graph-based representations can significantly improve the active speaker detection performance owing to its explicit spatial and temporal structure. SPELL outperforms all previous state-of-the-art approaches while
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2207.07783")
get_code_for_paper("2207.07783")
have("2207.07783")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2207.07783.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2207.07783)
Connect an agent — have() is free.