![SOK-Bench] Situation](https://aisholar.s3.ap-northeast-1.amazonaws.com/media/February2025/sok-bench-520x300.png)
SOK-Bench] Situational Video Inference Benchmark Using Real-World Knowledge In Video
SOK-Bench] Situational Video Inference Benchmark Using Real-World Knowledge In Video
Computer Vision
Computer Vision
Vript-Hard, A New Benchmark For Testing Comprehension Of Long-form Video
Vript-Hard, A New Benchmark For Testing Comprehension Of Long-form Video
Large Language Models
Machine Learning In Non-Euclidean Space Enabled By The Kuramoto Model
Machine Learning In Non-Euclidean Space Enabled By The Kuramoto Model
Computer Vision
![[InsectMamba] Classi](https://aisholar.s3.ap-northeast-1.amazonaws.com/media/August2024/insectmamba-520x300.png)
[InsectMamba] Classification Of Pests Using State Space Models To Support Smart Agriculture
[InsectMamba] Classification Of Pests Using State Space Models To Support Smart Agriculture
Computer Vision
![[CoMat] Resolve The](https://aisholar.s3.ap-northeast-1.amazonaws.com/media/August2024/comat_1_-520x300.png)
[CoMat] Resolve The Discrepancy Between Text And Image
[CoMat] Resolve The Discrepancy Between Text And Image
Computer Vision
![[OW-VISCap] Look Out](https://aisholar.s3.ap-northeast-1.amazonaws.com/media/August2024/ow-viscap-520x300.png)
[OW-VISCap] Look Out For Unseen Objects - A New Approach To Understanding Open World Video
[OW-VISCap] Look Out For Unseen Objects - A New Approach To Understanding Open World Video
Computer Vision
Assessing The Robustness Of Zero-shot Image Understanding Models Through CLIP
Assessing The Robustness Of Zero-shot Image Understanding Models Through CLIP
Contrastive Learning
![[VideoAgent] Underst](https://aisholar.s3.ap-northeast-1.amazonaws.com/media/June2024/videoagent-520x300.png)
[VideoAgent] Understanding Long-form Video Using A Large-scale Language Model As An Agent
[VideoAgent] Understanding Long-form Video Using A Large-scale Language Model As An Agent
Computer Vision
![[Segment Anything] Z](https://aisholar.s3.ap-northeast-1.amazonaws.com/media/June2024/segment_anything-520x300.png)
[Segment Anything] Zero-shot Segmentation Model
[Segment Anything] Zero-shot Segmentation Model
Segmentation
Apple Developed A Large Scale Autoregressive Image Model That Is Scalable Like An LLM.
Apple Developed A Large Scale Autoregressive Image Model That Is Scalable Like An LLM.
Computer Vision
![[Swin Transformer] T](https://aisholar.s3.ap-northeast-1.amazonaws.com/media/February2024/swin_transformer-520x300.png)
[Swin Transformer] Transformer-based Image Recognition Models To Keep Now!
[Swin Transformer] Transformer-based Image Recognition Models To Keep Now!
Image Recognition
![[DiffYOLO] Innovativ](https://aisholar.s3.ap-northeast-1.amazonaws.com/media/February2024/diffyolo-520x300.png)
[DiffYOLO] Innovative Framework Improves Object Detection With Low Quality Data
[DiffYOLO] Innovative Framework Improves Object Detection With Low Quality Data
Computer Vision
InstructPix2Pix: A New Model For Image Editing At The User's Direction
InstructPix2Pix: A New Model For Image Editing At The User's Direction
Computer Vision
![[mPLUG-Owl] Developi](https://aisholar.s3.ap-northeast-1.amazonaws.com/media/January2024/mplug-owl-520x300.png)
[mPLUG-Owl] Developing An LLM That Can Understand Images And Text
[mPLUG-Owl] Developing An LLM That Can Understand Images And Text
Computation And Language
T2I-Adapter: Frontiers In Text-to-Image Conversion Technology
T2I-Adapter: Frontiers In Text-to-Image Conversion Technology
Computer Vision
ImageBind: Bringing All Information Together To Create New Knowledge
ImageBind: Bringing All Information Together To Create New Knowledge
Machine Learning
[Set-of-Mark Visual Prompting] Prompting Technology To Enhance GPT-4V's Image Recognition Capability
[Set-of-Mark Visual Prompting] Prompting Technology To Enhance GPT-4V's Image Recognition Capability
Prompting Method
![[CoDi] Any-to-any Di](https://aisholar.s3.ap-northeast-1.amazonaws.com/media/December2023/composable_diffusion-520x300.png)
[CoDi] Any-to-any Diffusion Model That Can Handle Almost Any Modality
[CoDi] Any-to-any Diffusion Model That Can Handle Almost Any Modality
Diffusion Model