Related papers: Video Relationship Detection Using Mixture of Expe…
Recent advances in language and vision have demonstrated that scaling up model capacity consistently improves performance across diverse tasks. In 3D visual geometry reconstruction, large-scale training has likewise proven effective for…
Recent advances in dynamic scene reconstruction have significantly benefited from 3D Gaussian Splatting, yet existing methods show inconsistent performance across diverse scenes, indicating no single approach effectively handles all dynamic…
The rapid growth of video on the internet has made searching for video content using natural language queries a significant challenge. Human-generated queries for video datasets `in the wild' vary a lot in terms of degree of specificity,…
Mixture-of-Experts (MoE) models improve transformer efficiency but lack a unified theoretical explanation, especially when both feed-forward and attention layers are allowed to specialize. To this end, we study the Mixture-of-Transformers…
Pretrained vision-language models, such as CLIP, have demonstrated strong generalization capabilities, making them promising tools in the realm of zero-shot visual recognition. Visual relation detection (VRD) is a typical task that…
Different medical imaging modalities capture diagnostic information at varying spatial resolutions, from coarse global patterns to fine-grained localized structures. However, most existing vision-language frameworks in the medical domain…
Modeling feature interactions is essential for accurate click-through rate (CTR) prediction in advertising systems. Recent studies have adopted the Mixture-of-Experts (MoE) approach to improve performance by ensembling multiple feature…
Visual relations, such as "person ride bike" and "bike next to car", offer a comprehensive scene understanding of an image, and have already shown their great utility in connecting computer vision and natural language. However, due to the…
The Meta Video Dataset (MetaVD) provides annotated relations between action classes in major datasets for human action recognition in videos. Although these annotated relations enable dataset augmentation, it is only applicable to those…
Composed video retrieval (CoVR) is a challenging problem in computer vision which has recently highlighted the integration of modification text with visual queries for more sophisticated video search in large databases. Existing works…
We propose a novel mixture-of-experts class to optimize computer vision models in accordance with data transfer limitations at test time. Our approach postulates that the minimum acceptable amount of data allowing for highly-accurate…
To accurately understand engineering drawings, it is essential to establish the correspondence between images and their description tables within the drawings. Existing document understanding methods predominantly focus on text as the main…
Recent deep learning-based multi-view people detection (MVD) methods have shown promising results on existing datasets. However, current methods are mainly trained and evaluated on small, single scenes with a limited number of multi-view…
Adverse weather removal tasks like deraining, desnowing, and dehazing are usually treated as separate tasks. However, in practical autonomous driving scenarios, the type, intensity,and mixing degree of weather are unknown, so handling each…
Robust 3D object detection under adverse weather conditions is crucial for autonomous driving. However, most existing methods simply combine all weather samples for training while overlooking data distribution discrepancies across different…
This paper presents a comprehensive review of the Mixture-of-Experts (MoE) architecture in large language models, highlighting its ability to significantly enhance model performance while maintaining minimal computational overhead. Through…
Video-based person Re-Identification (V-ReID) aims to retrieve specific persons from raw videos captured by non-overlapped cameras. As a fundamental task, it spreads many multimedia and computer vision applications. However, due to the…
Computer vision researchers are embracing two promising paradigms: Vision Transformers (ViTs) and Multi-task Learning (MTL), which both show great performance but are computation-intensive, given the quadratic complexity of self-attention…
While Fourier-based neural operators are best suited to learning mappings between functions on periodic domains, several works have introduced techniques for incorporating non trivial boundary conditions. However, all previously introduced…
This paper presents Edge-based Mixture of Experts (MoE) Collaborative Computing (EMC2), an optimal computing system designed for autonomous vehicles (AVs) that simultaneously achieves low-latency and high-accuracy 3D object detection.…