Related papers: Learning Commonsense-aware Moment-Text Alignment f…
Visual grounding is a promising path toward more robust and accurate Natural Language Processing (NLP) models. Many multimodal extensions of BERT (e.g., VideoBERT, LXMERT, VL-BERT) allow a joint modeling of texts and images that lead to…
Referring video object segmentation aims to segment objects within a video corresponding to a given text description. Existing transformer-based temporal modeling approaches face challenges related to query inconsistency and the limited…
Unmanned aerial vehicles (UAVs) have become powerful platforms for real-time, high-resolution data collection, producing massive volumes of aerial videos. Efficient retrieval of relevant content from these videos is crucial for applications…
Large-scale video-language pre-training has made remarkable strides in advancing video-language understanding tasks. However, the heavy computational burden of video encoding remains a formidable efficiency bottleneck, particularly for…
Fine-grained image-text alignment is a pivotal challenge in multimodal learning, underpinning key applications such as visual question answering, image captioning, and vision-language navigation. Unlike global alignment, fine-grained…
Vision Language Models (VLMs) are typically evaluated with Visual Question Answering (VQA) tasks which assess a model's understanding of scenes. Good VQA performance is taken as evidence that the model will perform well on a broader range…
Test-time adaptation (TTA) of Vision-Language Models (VLMs) has emerged as a technique for tackling distribution shifts during the test time. Recent research indicates that the test-time adaptation is intrinsically linked to the model's…
Multi-channel video-language retrieval require models to understand information from different channels (e.g. video$+$question, video$+$speech) to correctly link a video with a textual response or query. Fortunately, contrastive multimodal…
Inspired by the dual-stream theory of the human visual system (HVS) - where the ventral stream is responsible for object recognition and detail analysis, while the dorsal stream focuses on spatial relationships and motion perception - an…
Vision-language tracking aims to locate the target object in the video sequence using a template patch and a language description provided in the initial frame. To achieve robust tracking, especially in complex long-term scenarios that…
Given a question-image input, the Visual Commonsense Reasoning (VCR) model can predict an answer with the corresponding rationale, which requires inference ability from the real world. The VCR task, which calls for exploiting the…
We address the problem of phrase grounding by lear ing a multi-level common semantic space shared by the textual and visual modalities. We exploit multiple levels of feature maps of a Deep Convolutional Neural Network, as well as…
Natural Language Video Grounding (NLVG) aims to localize time segments in an untrimmed video according to sentence queries. In this work, we present a new paradigm named Explore-And-Match for NLVG that seamlessly unifies the strengths of…
Video text-based visual question answering (Video TextVQA) task aims to answer questions about videos by leveraging the visual text appearing within the videos. This task poses significant challenges, requiring models to accurately perceive…
Large-scale video-language pre-training has shown significant improvement in video-language understanding tasks. Previous studies of video-language pretraining mainly focus on short-form videos (i.e., within 30 seconds) and sentences,…
We propose a new task and model for dense video object captioning -- detecting, tracking and captioning trajectories of objects in a video. This task unifies spatial and temporal localization in video, whilst also requiring fine-grained…
Language-driven action localization in videos is a challenging task that involves not only visual-linguistic matching but also action boundary prediction. Recent progress has been achieved through aligning language query to video segments,…
The reliance on language in Vision-Language-Action (VLA) models introduces ambiguity, cognitive overhead, and difficulties in precise object identification and sequential task execution, particularly in environments with multiple visually…
We propose to improve the time-sensitive video understanding (TSV) capability of video large language models (Video-LLMs) with grounded objects (GO). We hypothesize that TSV tasks can benefit from GO within frames, which is supported by our…
Unlike Object Detection, Visual Grounding task necessitates the detection of an object described by complex free-form language. To simultaneously model such complex semantic and visual representations, recent state-of-the-art studies adopt…