We introduce InternVideo2, a new video foundation model (ViFM) that achieves the state-of-
the-art performance in action recognition, video-text tasks, and video-centric dialogue. Our …

Abstract Language models are capable of commonsense reasoning: while domain-specific
models can learn from explicit knowledge (eg commonsense graphs [6], ethical norms [25]) …

As one of the most intuitive interfaces known to humans, natural language has the potential
to mediate many tasks that involve human-computer interaction, especially in application …

Audio captioning aims to generate text descriptions from environmental sounds. One
challenge of audio captioning is the difficulty of the generalization due to the lack of audio …

Large language models readily adapt to novel settings, even without task-specific training
data. Can their zero-shot capacity be extended to multimodal inputs? In this work, we …

This technical report describes the system submitted to the Detection and Classification of
Acoustic Scenes and Events (DCASE) 2022 challenge Task 6. There are two involving …

Sound can convey significant information for spatial reasoning in our daily lives. To endow
deep networks with such ability, we address the challenge of dense indoor prediction with …

The attention-based Transformers have been increasingly applied to audio classification
because of their global receptive field and ability to handle long-term dependency. However …

Compared with ample visual-text pre-training research, few works explore audio-text pre-
training, mostly due to the lack of sufficient parallel audio-text data. Most existing methods …

Aiming to locate the object that emits a specified sound in complex scenes, the task of
sounding object localization bridges two perception-oriented modalities of vision and …