Zero-shot semantic segmentation, which is developed to segment unseen categories, has attracted increasing attention due to its strong practicability. Previous approaches usually applied semantic-visual mapping based on seen categories to unseen categories, and thus failed to generate meaningful unseen visual representations and struggled to balance the seen and unseen concepts in the classiﬁer. To overcome the above limitations, we propose a novel meaningful learning method that could be embedded into any generation-based zero-shot semantic segmentation model, borrowing the idea from the educational psychology ﬁeld. The proposed meaningful learning method refers to the process that the new concepts could be learned by relating to existing comprehensible concepts and harmoniously incorporated into the concept schema. Speciﬁcally, we introduce a generator with conjugate conceptual correlation (G3C) which generates meaningful unseen visual information through anchoring into existing concepts. Moreover, simulating the rational thinking mechanism, we introduce a fast-slow concept modulator to alleviate the noisy over-correlation problem introduced by G3C and further construct a comprehensive concept schema. Extensive experiments conducted on three benchmarks demonstrate the superior performance of our method, especially according to the commonly-acknowledged h-mIoU (e.g., 4% improvement on the Pascal-VOC dataset).

A meaningful learning method for zero-shot semantic segmentation

This paper introduces our solution for Track 2 in AI City Challenge 2024. The task aims to solve traffic safety description and analysis with the dataset of Woven Traffic Safety (WTS), a real-world Pedestrian-Centric Traffic Video Dataset for Fine-grained Spatial-Temporal Understanding. Our solution mainly focuses on the following points: 1) To solve dense video captioning, we leverage the framework of dense video captioning with parallel decoding (PDVC) to model visual-language sequences and generate dense caption by chapters for video. 2) Our work leverages CLIP to extract visual features to more efficiently perform cross-modality training between visual and textual representations. 3) We conduct domain-specific model adaptation to mitigate domain shift problem that poses recognition challenge in video understanding. 4) Moreover, we leverage BDD-5K captioned videos to conduct knowledge transfer for better understanding WTS videos and more accurate captioning. Our solution has yielded on the test set, achieving 6th place in the competition. The open source code will be available at https://github.com/UCF-SST-Lab/AICity2024CVPRW

Enhancing Traffic Safety with Parallel Dense Video Captioning for End-to-End Event Analysis

Difficulty-aware prior-guided hierarchical network for adaptive segmentation of breast tumors

Lymph nodes are important peripheral immune organs in the human immune system, and a variety of systemic and restrictive diseases can attack lymph nodes, leading to changes in their morphology and structure. Accurate identification of lymph nodes is of great value for the diagnosis, treatment and subsequent evaluation of lymph node diseases. The article firstly proposes a multimodal image fusion method for image preprocessing based on the characteristics of lymph node ultrasound images, and then proposes DMA-UNet based on the UNet network model, which uses residual convolution blocks and multiscale dilated convolution blocks instead of the original single <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathbf{3} \ast\mathbf{3}$</tex> convolution in the codec structure, enabling the nodes of different sizes to be treated during feature extraction. Meanwhile, a hybrid attention mechanism is used in the jump-long connection path of the UNet network model, which solves the problem that the decoding layer will introduce useless noise and other information besides the detailed features of lymph nodes, and achieves better nodal segmentation results. 

Lymph Node Ultrasound Image Segmentation Algorithm Based on Multimodal Image Fusion and DMA-UNet

Social networks open up a new channel of video sharing and promote the scale and efficiency of video diffusion. Adjustable and scalable video diffusion is significant for the quality and performance of the service of video systems. In this paper, we propose a novel epidemic-based video diffusion strategy using awareness of sociality and mobility in wireless networks (EVDSM). EVDSM constructs a video diffusion model with the consideration of interest preference, social influence, and user mobility according to the roles and the propagation process of the Epidemic model. EVDSM designs an estimation method of interest preference according to content similarity and preference discrimination between videos; EVDSM designs an estimation method of user roles by investigation of interest preference and social influence to identify the video sharing behaviors of users and define the roles of users; EVDSM designs an estimation method of user mobility in terms of data transmission time and path structure stability. EVDSM proposes a control strategy of video diffusion, which formulates priority-based pairing between infectors and candidate infectors to achieve joint optimization of pairing success rate and delivery performance. The simulation results show how EVDSM achieves much better performance results in comparison with other state-of-the-art solutions.

/pdf/a-novel-epidemic-based-video-diffusion-strategy-using-1opsaspv.pdf

A Novel Epidemic-Based Video Diffusion Strategy Using Awareness of Sociality and Mobility in Wireless Networks

Difficulty-aware bi-network with spatial attention constrained graph for axillary lymph node segmentation

Video-moment location by query is a hot topic in video understanding. However, most of the existing methods ignore the importance of location efficiency in practical application scenarios; video and query sentences have to be fed into the network at the same time during the retrieval, which leads to low efficiency. To address this issue, in this study, we propose an efficient video moment location via hashing (VMLH). In the proposed method, query sentences and video clips are, respectively, converted into hash codes and hash code sets, in which the semantic similarity between query sentences and video clips is preserved. The location prediction network is designed to predict the corresponding timestamp according to the similarity among hash codes, and the videos do not need to be fed into the network during the process of retrieval and location. Furthermore, different from the existing methods, which require complex interactions and fusion between video and query sentences, the proposed VMLH method only needs a simple XOR operation among codes to locate the video moment with high efficiency. This paper lays the foundation for fast video clip positioning and makes it possible to apply large-scale video clip positioning in practice. The experimental results on two public datasets demonstrate the effectiveness of the method.

/pdf/vmlh-efficient-video-moment-location-via-hashing-26vus669.pdf

VMLH: Efficient Video Moment Location via Hashing

Popular Tasks used by Researchers

How can I help with your research?

Get more enhanced response by uploading the PDFs you want me to reference.

No relevant PDFs in your library

SciSpace is the AI research assistant for academics. Run systematic literature reviews on 280M+ papers, and write papers with cited sources. Trusted by 1M+ students, PhDs & researchers.

SciSpace | AI for Research

We encountered an error while loading the panel. Please try refreshing the page.

Something went wrong

Analyze PDFs

Code & Manuscripts

Funding & Grants

Literature & Patents

Medical & Clinical Data

Systematic Review

Visualize & Present

Web & Data

Build a Google Scholar-like website for your research.

Build a website

Create charts and images for your research

Create a Chart

Write a paper for submission to a journal

Draft a manuscript

Patent Search

Design eye-catching scientific posters in minutes.

Scientific Poster Generation

Systematic Literature Review

Anyone with the link can view this chat. You can switch it back to private anytime.

One task is running at the moment. Your messages will be shown right after.

Drag and drop or click here to browse

Loved by <highlight>1 million+</highlight> researchers

Extract a list of specific topics and their sources from unstructured text

Topics

Compare and analyze relevant papers that matches with your search

Papers

Get insights from PDFs and bookmarked papers from your library

My library

Recent searches

Try searching for:

Catch AI-generated content in scholarly and non-scholarly content

{ai} Detector

Ai Writer

Get PDF Summaries, highlighted text explanations 

Chat with PDF

Effortlessly create in-text citations and bibliographies in APA and 2,500 other formats

Citation generator

Get explanations, summaries, and answers on academic papers

Ease up your research workflow with {scispace}'s cohort of exciting AI tools

Elevate your academic writing skills and convey your ideas the way you want

Paraphraser

Explore our range of reading and writing tools

Your file is being prepared and should be ready in a few minutes. If it's a large file, it might take a bit longer. You can close this window, and we'll email you the file when it's done.

You have reached a maximum limit of <strong>{limit}</strong> columns in the table. Remove at least <strong>1</strong> column to add or create another one.

Chenglong Li

Author Tools

Chat about Author

Papers

Difficulty-aware bi-network with spatial attention constrained graph for axillary lymph node segmentation

VMLH: Efficient Video Moment Location via Hashing