news소식
29 items29건
TwelveLabs releases Pegasus 1.6, adding first-person video understanding, stronger entity recognition, native image analysis, and sharper visual comprehension.
TwelveLabs가 Pegasus 1.6을 출시했습니다. 1인칭 영상 이해, 더 정확해진 인물·사물 인식, 이미지 직접 분석, 더 정밀한 시각 이해가 더해졌습니다.
We launched Marengo 3.5, a video-native multimodal embedding model built around the temporal structure of video.
Marengo 3.5를 출시했습니다. 비디오의 시간 구조를 중심으로 만든 비디오 네이티브 멀티모달 임베딩 모델입니다.
TwelveLabs launches Pegasus 1.5, a video-language model for long-form video. In TwelveLabs’ own comparison, it outperformed Gemini 3.1 Pro on segmentation and multimodal prompting.
TwelveLabs가 롱폼 비디오를 위한 비디오-언어 모델 Pegasus 1.5를 출시했습니다. TwelveLabs가 자체 비교한 결과, 세그멘테이션과 멀티모달 프롬프팅에서 Gemini 3.1 Pro를 앞섰습니다.
TwelveLabs releases Marengo 3.0, a new standard for foundation models that understand the world in all its complexity.
TwelveLabs가 Marengo 3.0을 출시했습니다. 세상의 모든 복잡함을 이해하는 파운데이션 모델의 새로운 기준입니다.
One CVPR-2025 EVAL-FoMo 2 Workshop paper: Emergence of Text Readability in Vision Language Models.
CVPR 2025 EVAL-FoMo 2 워크숍 논문 한 편: Emergence of Text Readability in Vision Language Models.
I’ve started a new chapter at TwelveLabs!
TwelveLabs에서 새 출발을 했습니다!
One ICLR-2025 paper to appear: Probabilistic Language-Image Pre-Training (cited: 29).
ICLR 2025 게재 예정 논문 한 편: Probabilistic Language-Image Pre-Training (인용 29).
One AAAI-2025 paper to appear: Extract Free Dense Misalignment from CLIP (cited: 7).
AAAI 2025 게재 예정 논문 한 편: Extract Free Dense Misalignment from CLIP (인용 7).
One ECCV-2024 oral paper to appear: HYPE: Hyperbolic Entailment Filtering for Underspecified Images and Texts (cited: 29).
ECCV 2024 게재 예정 구두 발표(oral) 논문 한 편: HYPE: Hyperbolic Entailment Filtering for Underspecified Images and Texts (인용 29).
One ICML-2024 paper to appear: STELLA: Continual Audio-Video Pre-training with Spatio-Temporal Localized Alignment (cited: 9).
ICML 2024 게재 예정 논문 한 편: STELLA: Continual Audio-Video Pre-training with Spatio-Temporal Localized Alignment (인용 9).
One CHIL-2024 paper to appear: Vision-Language Generative Model for View-Specific Chest X-ray Generation (cited: 110).
CHIL 2024 게재 예정 논문 한 편: Vision-Language Generative Model for View-Specific Chest X-ray Generation (인용 110).
One CVPR-2024 paper to appear: Language-only Efficient Training of Zero-shot Composed Image Retrieval (cited: 193).
CVPR 2024 게재 예정 논문 한 편: Language-only Efficient Training of Zero-shot Composed Image Retrieval (인용 193).
One ICCV-2023 paper to appear: SeiT: Storage-Efficient Vision Training with Tokens Using 1% of Pixel Storage (cited: 16).
ICCV 2023 게재 예정 논문 한 편: SeiT: Storage-Efficient Vision Training with Tokens Using 1% of Pixel Storage (인용 16).
One ICLR-2023 paper: What Do Self-Supervised Vision Transformers Learn? (cited: 184).
ICLR 2023 논문 한 편: What Do Self-Supervised Vision Transformers Learn? (인용 184).
One ICLR-2022 paper: ViDT: An Efficient and Effective Fully Transformer-based Object Detector (cited: 172).
ICLR 2022 논문 한 편: ViDT: An Efficient and Effective Fully Transformer-based Object Detector (인용 172).
One CHI-2022 paper: Speeding up Inference with User Simulators through Policy Modulation.
CHI 2022 논문 한 편: Speeding up Inference with User Simulators through Policy Modulation.
One NeurIPS-2021 DGM workshop paper: Fourier-based Decoder for Periodic Signals (cited: 8).
NeurIPS 2021 DGM 워크숍 논문 한 편: Fourier-based Decoder for Periodic Signals (인용 8).
One ICML-2021 oral paper: Vision-and-Language Transformers (ViLT) (cited: 3,207).
ICML 2021 구두 발표(oral) 논문 한 편: Vision-and-Language Transformers (ViLT) (인용 3,207).
I joined Naver AI Lab.
Naver AI Lab에 합류했습니다.
One ECCV-2020 TASK-CV workshop oral paper: Diversified Mutual Deep Metric Learning (DM2) (cited: 11).
ECCV 2020 TASK-CV 워크숍 구두 발표(oral) 논문 한 편: Diversified Mutual Deep Metric Learning (DM2) (인용 11).
One NeurIPS-2019 paper: Dynamics of Attention for Focus Transition (DAFT) (cited: 12).
NeurIPS 2019 논문 한 편: Dynamics of Attention for Focus Transition (DAFT) (인용 12).