Related papers: MERLOT Reserve: Neural Script Knowledge through Vi…
Humans excel at spatial-temporal reasoning, effortlessly interpreting dynamic visual events from an egocentric viewpoint. However, whether multimodal large language models (MLLMs) can similarly understand the 4D world remains uncertain.…
We learn rich natural sound representations by capitalizing on large amounts of unlabeled sound data collected in the wild. We leverage the natural synchronization between vision and sound to learn an acoustic representation using…
Multimodal large language models (MLLMs) often struggle to ground reasoning in perceptual evidence. We present a systematic study of perception strategies-explicit, implicit, visual, and textual-across four multimodal benchmarks and two…
Multi-modal retrieval is an important problem for many applications, such as recommendation and search. Current benchmarks and even datasets are often manually constructed and consist of mostly clean samples where all modalities are…
Humans possess the remarkable ability to foresee the future to a certain extent based on present observations, a skill we term as foresight minds. However, this capability remains largely under explored within existing Multimodal Large…
Video understanding plays a vital role in bridging low-level visual signals with high-level cognitive reasoning, and is fundamental to applications such as autonomous driving, embodied AI, and the broader pursuit of AGI. The rapid…
Video-Text pre-training aims at learning transferable representations from large-scale video-text pairs via aligning the semantics between visual and textual information. State-of-the-art approaches extract visual features from raw pixels…
Advances in machine reading comprehension (MRC) rely heavily on the collection of large scale human-annotated examples in the form of (question, paragraph, answer) triples. In contrast, humans are typically able to generalize with only a…
Despite rapid advances in vision-language models (VLMs), current benchmarks for multimodal reasoning fall short in three key dimensions. First, they overwhelmingly rely on static images, failing to capture the temporal complexity of…
Video captioning is a challenging task that necessitates a thorough comprehension of visual scenes. Existing methods follow a typical one-to-one mapping, which concentrates on a limited sample space while ignoring the intrinsic semantic…
Multimodal large language models have fueled progress in image captioning. These models, fine-tuned on vast image datasets, exhibit a deep understanding of semantic concepts. In this work, we show that this ability can be re-purposed for…
Pretraining general-purpose visual features has become a crucial part of tackling many computer vision tasks. While one can learn such features on the extensively-annotated ImageNet dataset, recent approaches have looked at ways to allow…
Audio is essential for multimodal video understanding. On the one hand, video inherently contains audio, which supplies complementary information to vision. Besides, video large language models (Video-LLMs) can encounter many audio-centric…
World models have demonstrated impressive performance on robotic learning tasks. Many such tasks inherently demand multimodal reasoning; for example, filling a bottle with water will lead to visual information alone being ambiguous or…
We present a simplified, task-agnostic multi-modal pre-training approach that can accept either video or text input, or both for a variety of end tasks. Existing pre-training are task-specific by adopting either a single cross-modal encoder…
Stories are a very compelling medium to convey ideas, experiences, social and cultural values. Narrative is a specific manifestation of the story that turns it into knowledge for the audience. In this paper, we propose a machine learning…
Video-Question-Answering (VideoQA) comprises the capturing of complex visual relation changes over time, remaining a challenge even for advanced Video Language Models (VLM), i.a., because of the need to represent the visual content to a…
Pre-trained Language Models (PLMs) have achieved great success on Machine Reading Comprehension (MRC) over the past few years. Although the general language representation learned from large-scale corpora does benefit MRC, the poor support…
Video Reasoning Segmentation (VRS) aims to segment target objects in videos based on implicit instructions that convey human intent and temporal logic. Existing MLLM-based methods predict masks with a [SEG] token after selecting frames via…
We introduce a novel self-supervised pretext task for learning representations from audio-visual content. Prior work on audio-visual representation learning leverages correspondences at the video level. Approaches based on audio-visual…