Related papers: MoLo: Motion-augmented Long-short Contrastive Lear…

Few-shot action recognition aims to enable models to quickly learn new action categories from limited labeled samples, addressing the challenge of data scarcity in real-world applications. Current research primarily addresses three core…

Many few-shot learning models focus on recognising images. In contrast, we tackle a challenging task of few-shot action recognition from videos. We build on a C3D encoder for spatio-temporal video blocks to capture short-range action…

Recent unsupervised multi-object detection models have shown impressive performance improvements, largely attributed to novel architectural inductive biases. Unfortunately, they may produce suboptimal object encodings for downstream tasks.…

A critical approach for efficiently deploying Mixture-of-Experts (MoE) models with massive parameters is quantization. However, state-of-the-art MoE models suffer from non-negligible accuracy loss with extreme quantization, such as under 4…

Learning-based multi-view stereo (MVS) methods have made impressive progress and surpassed traditional methods in recent years. However, their accuracy and completeness are still struggling. In this paper, we propose a new method to enhance…

Video moment retrieval is a challenging task requiring fine-grained interactions between video and text modalities. Recent work in image-text pretraining has demonstrated that most existing pretrained models suffer from information…

Large-scale multimodal foundation models, particularly Contrastive Captioners (CoCa), have achieved state-of-the-art results by unifying contrastive alignment with generative captioning. While zero-shot transfer capabilities are…

We address the problem of few-shot semantic segmentation (FSS), which aims to segment novel class objects in a target image with a few annotated samples. Though recent advances have been made by incorporating prototype-based metric…

This paper introduces a joint learning architecture (JLA) for multiple object tracking (MOT) and trajectory forecasting in which the goal is to predict objects' current and future trajectories simultaneously. Motion prediction is widely…

In this paper, we consider the problem of temporal action localization under low-shot (zero-shot & few-shot) scenario, with the goal of detecting and classifying the action instances from arbitrary categories within some untrimmed videos,…

Despite excellent progress has been made, the performance on action recognition still heavily relies on specific datasets, which are difficult to extend new action classes due to labor-intensive labeling. Moreover, the high diversity in…

Universal Multimodal embedding models built on Multimodal Large Language Models (MLLMs) have traditionally employed contrastive learning, which aligns representations of query-target pairs across different modalities. Yet, despite its…

This paper strives for motion-focused video-language representations. Existing methods to learn video-language representations use spatial-focused data, where identifying the objects and scene is often enough to distinguish the relevant…

This work proposes a new end-to-end DCNN based approach for motion segmentation, especially for video sequences captured with such non-static cameras, called MOSNET. While other approaches focus on spatial or temporal context only, the…

Given a collection of untrimmed and unsegmented videos, video corpus moment retrieval (VCMR) is to retrieve a temporal moment (i.e., a fraction of a video) that semantically corresponds to a given text query. As video and text are from two…

Distance metric learning (DML) has been successfully applied to object classification, both in the standard regime of rich training data and in the few-shot scenario, where each category is represented by only a few examples. In this work,…

Leveraging spatiotemporal information in videos is critical for weakly supervised video object localization (WSVOL) tasks. However, state-of-the-art methods only rely on visual and motion cues, while discarding discriminative information,…

Contrastive self-supervised learning methods learn to map data points such as images into non-parametric representation space without requiring labels. While highly successful, current methods require a large amount of data in the training…

Feature matching across video streams remains a cornerstone challenge in computer vision. Increasingly, robust multimodal matching has garnered interest in robotics, surveillance, remote sensing, and medical imaging. While traditional rely…

The prior self-supervised learning researches mainly select image-level instance discrimination as pretext task. It achieves a fantastic classification performance that is comparable to supervised learning methods. However, with degraded…