satolab12

satolab12's Stars

• LLaVA-VL/LLaVA-NeXT

  Language:Python3.2k282

• okankop/vidaug

  Effective Video Augmentation Techniques for Training Convolutional Neural Networks

  Language:Python39179

• VisionLearningGroup/SSDA_MME

  Semi-supervised Domain Adaptation via Minimax Entropy

  Language:Python30147

• ayushtues/ADDA_pytorch

  Pytorch implementation of Adversarial Discriminative Domain Adaptation

  Language:Python103

• erictzeng/adda

  Language:Python22476

• fungtion/DANN

  pytorch implementation of Domain-Adversarial Training of Neural Networks

  Language:Python860155

• adapt-python/adapt

  Awesome Domain Adaptation Python Toolbox

  Language:Python31945

• tim-learn/DINE

  code for our CVPR 2022 paper "DINE: Domain Adaptation from Single and Multiple Black-box Predictors"

  Language:Python787

• tim-learn/awesome-test-time-adaptation

  Collection of awesome test-time (domain/batch/instance) adaptation methods

  80855

• vishal-siddegowda/CrowdAnomalyDetection_DeepLearning

  In the recent times, machine learning and deep learning have demonstrated an key advancement in the field of anomaly detection especially in the crowd. This progress has impacted immensely in detecting suspicious/abnormal activity such as robbery, vandalism, stempedes, road rage, and so on. For the purpose of this study, transfer learning is employed because of it proven efficiency to train on a small dataset yet producing a promising output. Transfer learning is utilized to train the dataset using Visual Geometry Group network 19 (VGGNet-19) and Visual Geometry Group network 16 (VGGNet-16) pre-trained network to extract the human motion features from a RGB video data. The designed model is employed on two dataset, UMN(University of Minnesota) and WEB crowd dataset to achieve the objective. Analysing the experimental results, VGGNet-19 has been demonstrated a good quality performance of approximately 98% on UMN data while VGGNet-16 has produced a approximately 58% on WEB dataset.

  Language:Jupyter Notebook31

• v-iashin/video_features

  Extract video features from raw videos using multiple GPUs. We support RAFT flow frames as well as S3D, I3D, R(2+1)D, VGGish, CLIP, and TIMM models.

  Language:Python55397

• yyuanad/Pytorch_C3D_Feature_Extractor

  Pytorch C3D feature extractor

  Language:Python13135

• RupertLuo/Valley

  The official repository of "Video assistant towards large language model makes everything easy"

  Language:Python21514

• seqam-lab/DMVAE

  Language:Python154

• xaggi/claws_eccv

  Project page for the 'CLAWS: Clustering Assisted Weakly Supervised Learning with Normalcy Suppression for Anomalous Event Detection', ECCV 2020 paper.

  124

• xiaobai1217/Awesome-Video-Datasets

  Video datasets

  1.3k96

• TeCSAR-UNCC/CHAD

  132

• yahoojapan/ja-vg-vqa

  28

• TinyLLaVA/TinyLLaVA_Factory

  A Framework of Small-scale Large Multimodal Models

  Language:Python70275

• zhuyiche/llava-phi

  Language:Python38138

• bdytx5/finetune_LLaVA

  Language:Python297

• tosiyuki/LLaVA-JP

  LLaVA-JP is a Japanese VLM trained by LLaVA method

  Language:Python5713

• fesvhtr/CUVA

  [CVPR 2024] Official repository of the paper "Uncovering What, Why and How: A Comprehensive Benchmark for Causation Understanding of Video Anomaly"

  Language:Python6922

• zackschen/CoIN

  Instruction Tuning in Continual Learning paradigm

  Language:Python352

• wyzjack/Awesome-XAD

  Paper and Dataset Summary for paper "Explainable Anomaly Detection in Images and Videos: A Survey"

  232

• longtanle/awesome-federated-LLM-learning

  This is a collection of research papers for Federated Learning for Large Language Models (FedLLM). And the repository will be continuously updated to track the frontier of FedLLM.

  761

• lucazanella/lavad

  Official implementation of "Harnessing Large Language Models for Training-free Video Anomaly Detection", CVPR 2024

  Language:Python653

• haotian-liu/LLaVA

  [NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

  Language:Python21k2.3k

• openai/CLIP

  CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

  Language:Jupyter Notebook26.8k3.4k

• pipixin321/HolmesVAD

  Official implementation of "Holmes-VAD: Towards Unbiased and Explainable Video Anomaly Detection via Multi-modal LLM"

  Language:Python893