In this work, we introduce Vid2Seq, a multi-modal single-stage dense event captioning model pretrained on narrated videos which are readily-available at scale. The Vid2Seq architecture augments a language model with special time tokens, allowing it to seamlessly predict event boundaries and textual descriptions in the same output sequence. Such a unified model requires large-scale training data, which is not available in current annotated datasets. We show that it is possible to leverage unlabeled narrated videos for dense video captioning, by reformulating sentence boundaries of transcribed speech as pseudo event boundaries, and using the transcribed speech sentences as pseudo event captions. The resulting Vid2Seq model pretrained on the YT-Temporal-1B dataset improves the state of the art on a variety of dense video captioning benchmarks including YouCook2, ViTT and ActivityNet Captions. Vid2Seq also generalizes well to the tasks of video paragraph captioning and video clip captioning, and to few-shot settings. Our code is publicly available at https://antoyang.github.io/vid2seq.html.

Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning

Recent studies have shown promising results on utilizing pre-trained image-language models for video question answering. While these image-language models can efficiently bootstrap the representation learning of video-language models, they typically concatenate uniformly sampled video frames as visual inputs without explicit language-aware, temporal modeling. When only a portion of a video input is relevant to the language query, such uniform frame sampling can often lead to missing important visual cues. Although humans often find a video moment to focus on and rewind the moment to answer questions, training a query-aware video moment localizer often requires expensive annotations and high computational costs. To address this issue, we propose Self-Chained Video Localization-Answering (SeViLA), a novel framework that leverages a single image-language model (BLIP-2) to tackle both temporal keyframe localization and QA on videos. SeViLA framework consists of two modules: Localizer and Answerer, where both are parameter-efficiently fine-tuned from BLIP-2. We chain these modules for cascaded inference and self-refinement. First, in the forward chain, the Localizer finds multiple language-aware keyframes in a video, which the Answerer uses to predict the answer. Second, in the reverse chain, the Answerer generates keyframe pseudo-labels to refine the Localizer, alleviating the need for expensive video moment localization annotations. SeViLA outperforms several strong baselines/previous works on five video QA and event prediction tasks, and achieves the state-of-the-art in both fine-tuning (NExT-QA, STAR) and zero-shot (NExT-QA, STAR, How2QA, VLEP) settings. We show a comprehensive analysis, e.g., the impact of Localizer, comparisons of Localizer with other temporal localization models, pre-training/self-refinement of Localizer, and varying the number of keyframes.

Self-Chained Image-Language Model for Video Localization and Question Answering

Question generation in natural language has a wide variety of applications. It can be a helpful tool for chatbots for generating interesting questions as also for automating the process of question generation from a piece of text. Most modern-day systems, which are conversational, require question generation ability for identifying the user’s needs and serving customers better. Generating questions in natural language is now, a more evolved task, which also includes generating questions for an image or video. In this review, we provide an overview of the research progress in automatic question generation. We also present a comprehensive literature review covering the classification of Question Generation systems by categorizing them into three broad use-cases, namely standalone question generation, visual question generation, and conversational question generation. We next discuss the datasets available for the same for each use-case. We further direct this review towards applications of question generation and discuss the challenges in this field of research. 

https://link.springer.com/content/pdf/10.1007/s13748-023-00295-9.pdf

Automatic question generation: a review of methodologies, datasets, evaluation metrics, and applications

Generative Pre-trained Transformer (GPT) based model with relative attention for de novo drug design.

Data balancing is a known technique for improving the performance of classification tasks. In this work we define a novel balancing-viageneration framework termed BalaGen. BalaGen consists of a flexible balancing policy coupled with a text generation mechanism. Combined, these two techniques can be used to augment a dataset for more balanced distribution. We evaluate BalaGen on three publicly available semantic utterance classification (SUC) datasets. One of these is a new COVID-19 Q&A dataset published here for the first time. Our work demonstrates that optimal balancing policies can significantly improve classifier performance, while augmenting just part of the classes and under-sampling others. Furthermore, capitalizing on the advantages of balancing, we show its usefulness in all relevant BalaGen framework components. We validate the superiority of BalaGen on ten semantic utterance datasets taken from real-life goaloriented dialogue systems. Based on our results we encourage using data balancing prior to training for text classification tasks.

Balancing via Generation for Multi-Class Text Classification Improvement

Drug discovery for a protein target is a laborious and costly process. Deep learning (DL) methods have been applied to drug discovery and successfully generated novel molecular structures, and they can substantially reduce development time and costs. However, most of them rely on prior knowledge, either by drawing on the structure and properties of known molecules to generate similar candidate molecules or extracting information on the binding sites of protein pockets to obtain molecules that can bind to them. In this paper, DeepTarget, an end-to-end DL model, was proposed to generate novel molecules solely relying on the amino acid sequence of the target protein to reduce the heavy reliance on prior knowledge. DeepTarget includes three modules: Amino Acid Sequence Embedding (AASE), Structural Feature Inference (SFI), and Molecule Generation (MG). AASE generates embeddings from the amino acid sequence of the target protein. SFI inferences the potential structural features of the synthesized molecule, and MG seeks to construct the eventual molecule. The validity of the generated molecules was demonstrated by a benchmark platform of molecular generation models. The interaction between the generated molecules and the target proteins was also verified on the basis of two metrics, drug-target affinity and molecular docking. The results of the experiments indicated the efficacy of the model for direct molecule generation solely conditioned on amino acid sequence. 

/pdf/deep-generative-model-for-drug-design-from-protein-target-1od2uadi.pdf

Deep generative model for drug design from protein target sequence

Object detection of overhead transmission lines is a solution for promoting inspection efficiency for power companies. However, aerial images contain many complex backgrounds and small objects, and traditional algorithms are incompetent in the identification of details of power transmission lines accurately. To address this problem, this paper develops an object detection method based on optimized You Only Look Once v5-small (YOLOv5s). This method is designed to be engineering-friendly, with the objective of maximal detection accuracy and computation simplicity. Firstly, to improve the detecting accuracy of small objects, a larger scale detection layer and jump connections are added to the network. Secondly, a self-attention mechanism is adopted to merge the feature relationships between spatial and channel dimensions, which could suppress the interference of complex backgrounds and boost the salience of objects. In addition, a small object enhanced Complete Intersection over Union (CIoU) is put forward as the loss function of the bounding box regression. This loss function could increase the derived loss for small objects automatically, thereby improving the detection of small objects. Furthermore, based on the scaling factors of batch-normalization layers, a pruning method is adopted to reduce the parameters and achieve a lightweight method. Finally, case studies are fulfilled by comparing the proposed method with classic YOLOv5s, which demonstrate that the detection accuracy is increased by 4%, the model size is reduced by 58%, and the detection speed is raised by 3.3%.

/pdf/research-on-object-detection-of-overhead-transmission-lines-15ukotko.pdf

Research on Object Detection of Overhead Transmission Lines Based on Optimized YOLOv5s

Despite recent progress in video and language representation learning, the weak or sparse correspondence between the two modalities remains a bottleneck in the area. Most video-language models are trained via pair-level loss to predict whether a pair of video and text is aligned. However, even in paired video-text segments, only a subset of the frames are semantically relevant to the corresponding text, with the remainder representing noise; where the ratio of noisy frames is higher for longer videos. We propose FineCo (Fine-grained Contrastive Loss for Frame Sampling), an approach to better learn video and language representations with a fine-grained contrastive objective operating on video frames. It helps distil a video by selecting the frames that are semantically equivalent to the text, improving cross-modal correspondence. Building on the well established VideoCLIP model as a starting point, FineCo achieves state-of-the-art performance on YouCookII, a text-video retrieval benchmark with long videos. FineCo also achieves competitive results on text-video retrieval (MSR-VTT), and video question answering datasets (MSR-VTT QA and MSR-VTT MC) with shorter videos.

Contrastive Video-Language Learning with Fine-grained Frame Sampling

A major obstacle to the development of Natural Language Processing (NLP) methods in the biomedical domain is data accessibility. This problem can be addressed by generating medical data artificially. Most previous studies have focused on the generation of short clinical text, and evaluation of the data utility has been limited. We propose a generic methodology to guide the generation of clinical text with key phrases. We use the artificial data as additional training data in two key biomedical NLP tasks: text classification and temporal relation extraction. We show that artificially generated training data used in conjunction with real training data can lead to performance boosts for data-greedy neural network algorithms. We also demonstrate the usefulness of the generated data for NLP setups where it fully replaces real training data.

/pdf/is-artificial-data-useful-for-biomedical-natural-language-4h42zrpplt.pdf

Is artificial data useful for biomedical Natural Language Processing algorithms

Handle everyday research tasks with reliable, citation-backed results

Your personal Research Agent to handle research tasks with citation-backed results

Popular Tasks used by Researchers

How can I help with your research?

Meet SciSpace

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

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

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.

Zixu Wang

Author Tools

Chat about Author

Papers

Deep generative model for drug design from protein target sequence

Research on Object Detection of Overhead Transmission Lines Based on Optimized YOLOv5s

Contrastive Video-Language Learning with Fine-grained Frame Sampling

Is artificial data useful for biomedical Natural Language Processing algorithms

Is artificial data useful for biomedical Natural Language Processing algorithms