https://github.com/ASU-APG/TragedyPlusTime
공식 코드Tragedy Plus Time: Capturing Unintended Human Activities from Weakly-labeled Videos
Papers with Code 아카이브
Video Captioning
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 6
- 평가표
- 13
- 보존된 평가 기록
- 86
Video Captioning is a task of automatic captioning a video by understanding the action and event in the video which can help in the retrieval of the video efficiently through text.
Source: NITS-VC System for VATEX Video Captioning Challenge 2020
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/HuiGuanLab/ms-sl
공식 코드https://github.com/HumamAlwassel/TSP
공식 코드TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks
https://github.com/InnovArul/vidreid_cosegmentation
공식 코드Co-segmentation Inspired Attention Module for Video-based Computer Vision Tasks
https://github.com/LLebronC/TRECvid-VTT_HA
공식 코드BERTHA: Video Captioning Evaluation Via Transfer-Learned Human Assessment
https://github.com/LUNAProject22/CLIPSitu
공식 코드Effectively Leveraging CLIP for Generating Situational Summaries of Images and Videos
https://github.com/LightGal/VideoTitling
공식 코드Comprehensive Information Integration Modeling Framework for Video Titling
https://github.com/MichiganNLP/video-fill-in-the-blank
공식 코드FIBER: Fill-in-the-Blanks as a Challenging Video Understanding Evaluation Framework
https://github.com/OSUPCVLab/VideoToTextDNN
공식 코드MTLE: A Multitask Learning Encoder of Visual Feature Representations for Video and Movie Description
https://github.com/PaddlePaddle/PaddleVideo/blob/develop/docs/en/model_zoo/multimodal/actbert.md
공식 코드https://github.com/ParitoshParmar/MTL-AQA
공식 코드What and How Well You Performed? A Multitask Learning Approach to Action Quality Assessment
https://github.com/SCZwangxiao/RTQ-MM2023
공식 코드RTQ: Rethinking Video-language Understanding Based on Image-text Model
https://github.com/Sha-Lab/CMHSE
공식 코드https://github.com/ShipingGe/ILCACM
공식 코드https://github.com/Skyline-9/Shotluck-Holmes
공식 코드https://github.com/TXH-mercury/VALOR
공식 코드VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset
https://github.com/UARK-AICV/VLCAP
공식 코드VLCap: Vision-Language with Contrastive Learning for Coherent Video Paragraph Captioning
https://github.com/VALUE-Leaderboard/StarterCode
공식 코드VALUE: A Multi-Task Benchmark for Video-and-Language Understanding Evaluation
https://github.com/VisionLearningGroup/JEDDi-Net
공식 코드Joint Event Detection and Description in Continuous Video Streams
https://github.com/WingsBrokenAngel/MSR-VTT-DataCleaning
공식 코드https://github.com/WingsBrokenAngel/Semantics-AssistedVideoCaptioning
공식 코드A Semantics-Assisted Video Captioning Model Trained with Scheduled Sampling
https://github.com/WingsBrokenAngel/delving-deeper-into-the-decoder-for-video-captioning
공식 코드https://github.com/aalto-cbir/neuraltalkTheano
공식 코드https://github.com/acherstyx/CoCap
공식 코드https://github.com/adwardlee/multitask-end-to-end-video-captioning
공식 코드End-to-End Video Captioning with Multitask Reinforcement Learning
https://github.com/adymaharana/StoryViz
공식 코드Improving Generation and Evaluation of Visual Stories via Semantic Consistency
https://github.com/adymaharana/storydalle
공식 코드StoryDALL-E: Adapting Pretrained Text-to-Image Transformers for Story Continuation
https://github.com/ailab-kyunghee/cm2_dvc
공식 코드Do You Remember? Dense Video Captioning with Cross-Modal Memory Retrieval
https://github.com/aimagelab/mvad-names-dataset
공식 코드https://github.com/aimagelab/pacscore
공식 코드Positive-Augmented Contrastive Learning for Image and Video Captioning Evaluation
https://github.com/ajd12342/why-winoground-hard
공식 코드Why is Winoground Hard? Investigating Failures in Visuolinguistic Compositionality
https://github.com/alanaai/evud
공식 코드AlanaVLM: A Multimodal Embodied AI Foundation Model for Egocentric Video Understanding
https://github.com/alibaba/AliceMind
공식 코드mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video
https://github.com/baiyang4/d-lsg-video-caption
공식 코드https://github.com/bladewaltz1/promptswitch
공식 코드Prompt Switch: Efficient CLIP Adaptation for Text-Video Retrieval
https://github.com/boheumd/MA-LMM
공식 코드MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.