paper-with-me

Papers

SCANet: Scene Complexity Aware Network for Weakly-Supervised Video Moment Retrieval

2023-10-08 · ICCV 2023 1 · Sunjae Yoon, Gwanhyeong Koo, Dahyun Kim, Chang D. Yoo

Video moment retrieval aims to localize moments in video corresponding to a given language query. To avoid the expensive cost of annotating the temporal moments, weakly-supervised VMR (wsVMR) systems have been studied. For such systems, generating a number of proposals as moment candidates and then selecting the most appropriate proposal has been a popular approach. These proposals are assumed to contain many distinguishable scenes in a video as candidates. However, existing proposals of wsVMR systems do not respect the varying numbers of scenes in each video, where the proposals are heuristically determined irrespective of the video. We argue that the retrieval system should be able to counter the complexities caused by varying numbers of scenes in each video. To this end, we present a novel concept of a retrieval system referred to as Scene Complexity Aware Network (SCANet), which measures the `scene complexity' of multiple scenes in each video and generates adaptive proposals responding to variable complexities of scenes in each video. Experimental results on three retrieval benchmarks (i.e., Charades-STA, ActivityNet, TVR) achieve state-of-the-art performances and demonstrate the effectiveness of incorporating the scene complexity.

📄 PDF Abstract BibTeX arXiv:2310.05241

Code (0)

등록된 구현이 없습니다.

Tasks

Moment RetrievalRetrieval

Methods 이 논문이 사용한 방법론

AWARE We propose to theoretically and empirically examine the effect of incorporating weighting schemes into walk-aggregating GNNs. To this end, we propose a simple, interpretable, and…

Similar Papers 제목 키워드 기반

SCANet: Self-Paced Semi-Curricular Attention Network for Non-Homogeneous Image Dehazing

2023-04-17 · Yu Guo, Yuan Gao, Ryan Wen Liu, Yuxu Lu 외

The presence of non-homogeneous haze can cause scene blurring, color distortion, low contrast, and other degradations that obscure texture details. Existing homogeneous dehazing methods struggle to handle the non-uniform…

Image Dehazing

MS-SCANet: A Multiscale Transformer-Based Architecture with Dual Attention for No-Reference Image Quality Assessment

2026-02-03 · Mayesha Maliha R. Mithila, Mylene C. Q. Farias arxiv

We present the Multi-Scale Spatial Channel Attention Network (MS-SCANet), a transformer-based architecture designed for no-reference image quality assessment (IQA). MS-SCANet features a dual-branch structure that process…

No-Reference Image Quality Assessment

Segregation and Context Aggregation Network for Real-time Cloud Segmentation

2025-04-19 · Yijie Li, Hewei Wang, Jiayi Zhang, Jinjiang You 외

Cloud segmentation from intensity images is a pivotal task in atmospheric science and computer vision, aiding weather forecasting and climate analysis. Ground-based sky/cloud segmentation extracts clouds from images for …

Computational EfficiencySegmentationWeather Forecasting

SA-MixNet: Structure-aware Mixup and Invariance Learning for Scribble-supervised Road Extraction in Remote Sensing Images

2024-03-03 · Jie Feng, Hao Huang, Junpeng Zhang, Weisheng Dong 외

Mainstreamed weakly supervised road extractors rely on highly confident pseudo-labels propagated from scribbles, and their performance often degrades gradually as the image scenes tend various. We argue that such degrada…

FCL-COD: Weakly Supervised Camouflaged Object Detection with Frequency-aware and Contrastive Learning

2026-03-24 · Jingchen Ni, Quan Zhang, Dan Jiang, Keyu Lv 외 arxiv

Existing camouflage object detection (COD) methods typically rely on fully-supervised learning guided by mask annotations. However, obtaining mask annotations is time-consuming and labor-intensive. Compared to fully-supe…

Representation LearningContrastive LearningObject Detection