Dynamic Graph Representation Learning for Video Dialog via Multi-Modal Shuffled Transformers
Keywords:Language and Vision, Video Understanding & Activity Analysis, Question Answering, Language Grounding & Multi-modal NLP
AbstractGiven an input video, its associated audio, and a brief caption, the audio-visual scene aware dialog (AVSD) task requires an agent to indulge in a question-answer dialog with a human about the audio-visual content. This task thus poses a challenging multi-modal representation learning and reasoning scenario, advancements into which could influence several human-machine interaction applications. To solve this task, we introduce a semantics-controlled multi-modal shuffled Transformer reasoning framework, consisting of a sequence of Transformer modules, each taking a modality as input and producing representations conditioned on the input question. Our proposed Transformer variant uses a shuffling scheme on their multi-head outputs, demonstrating better regularization. To encode fine-grained visual information, we present a novel dynamic scene graph representation learning pipeline that consists of an intra-frame reasoning layer producing spatio-semantic graph representations for every frame, and an inter-frame aggregation module capturing temporal cues. Our entire pipeline is trained end-to-end. We present experiments on the benchmark AVSD dataset, both on answer generation and selection tasks. Our results demonstrate state-of-the-art performances on all evaluation metrics.
How to Cite
Geng, S., Gao, P., Chatterjee, M., Hori, C., Le Roux, J., Zhang, Y., Li, H., & Cherian, A. (2021). Dynamic Graph Representation Learning for Video Dialog via Multi-Modal Shuffled Transformers. Proceedings of the AAAI Conference on Artificial Intelligence, 35(2), 1415-1423. https://doi.org/10.1609/aaai.v35i2.16231
AAAI Technical Track on Computer Vision I