Related papers: MDMMT: Multidomain Multimodal Transformer for Vide…

Multimodal pre-training models, such as LXMERT, have achieved excellent results in downstream tasks. However, current pre-trained models require large amounts of training data and have huge model sizes, which make them difficult to apply in…

Vision-Language Models have made significant progress on many perception-focused tasks. However, their progress on reasoning-focused tasks remains limited due to the lack of high-quality and diverse training data. In this work, we aim to…

Multimodal retrieval systems are becoming increasingly vital for cutting-edge AI technologies, such as embodied AI and AI-driven digital content industries. However, current multimodal retrieval tasks lack sufficient complexity and…

Multimodal machine translation (MMT) systems have been shown to outperform their text-only neural machine translation (NMT) counterparts when visual context is available. However, recent studies have also shown that the performance of MMT…

Action recognition and localization in complex, untrimmed videos remain a formidable challenge in computer vision, largely due to the limitations of existing methods in capturing fine-grained actions, long-term temporal dependencies, and…

The rapid advancement of Multimodal Large Language Models (MLLMs) has extended CLIP-based frameworks to produce powerful, universal embeddings for retrieval tasks. However, existing methods primarily focus on natural images, offering…

Multi-camera tracking plays a pivotal role in various real-world applications. While end-to-end methods have gained significant interest in single-camera tracking, multi-camera tracking remains predominantly reliant on heuristic techniques.…

Video Moment Retrieval (VMR) aims to localize a specific temporal segment within an untrimmed long video given a natural language query. Existing methods often suffer from inadequate training annotations, i.e., the sentence typically…

Information retrieval methods often rely on a single embedding model trained on large, general-domain datasets like MSMARCO. While this approach can produce a retriever with reasonable overall performance, they often underperform models…

Multimodal retrieval is the task of aggregating information from queries across heterogeneous modalities to retrieve desired targets. State-of-the-art multimodal retrieval models can understand complex queries, yet they are typically…

Video-text retrieval has many real-world applications such as media analytics, surveillance, and robotics. This paper presents the 1st place solution to the video retrieval track of the ICCV VALUE Challenge 2021. We present a simple yet…

Current methods for Video Moment Retrieval (VMR) struggle to align complex situations involving specific environmental details, character descriptions, and action narratives. To tackle this issue, we propose a Large Language Model-guided…

In this paper we tackle the cross-modal video retrieval problem and, more specifically, we focus on text-to-video retrieval. We investigate how to optimally combine multiple diverse textual and visual features into feature pairs that lead…

This paper presents a new method for end-to-end Video Question Answering (VideoQA), aside from the current popularity of using large-scale pre-training with huge feature extractors. We achieve this with a pyramidal multimodal transformer…

Recently, numbers of works shows that the performance of neural machine translation (NMT) can be improved to a certain extent with using visual information. However, most of these conclusions are drawn from the analysis of experimental…

Multimodal embedding models aim to map heterogeneous inputs, such as text, images, videos, and audio, into a shared semantic space. However, existing methods and benchmarks remain largely limited to partial modality coverage, making it…

Deep learning-based Multiple Object Tracking (MOT) currently relies on off-the-shelf detectors for tracking-by-detection.This results in deep models that are detector biased and evaluations that are detector influenced. To resolve this…

Video super-resolution (VSR) aims at restoring a video in low-resolution (LR) and improving it to higher-resolution (HR). Due to the characteristics of video tasks, it is very important that motion information among frames should be well…

Video captioning automatically generates short descriptions of the video content, usually in form of a single sentence. Many methods have been proposed for solving this task. A large dataset called MSR Video to Text (MSR-VTT) is often used…

An increasing number of datasets contain multiple views, such as video, sound and automatic captions. A basic challenge in representation learning is how to leverage multiple views to learn better representations. This is further…