논문 리뷰

1.NoPe-NeRF: Optimising Neural Radiance Field with No Pose Prior

post-thumbnail

2.Legal Judgment Prediction via Event Extraction with Constraint

post-thumbnail

3.LEGAL-BERT: The Muppets straight out of Law Schoo

post-thumbnail

4.ShapeGPT: 3D Shape Generation with A Unified Multi-modal Language Model

post-thumbnail

5.PoseScript: Linking 3D Human Poses and Natural Language

post-thumbnail

6.Unsupervised Keyphrase Extraction via Interpretable Neural Networks

post-thumbnail

7.InterFusion: Text-Driven Generation of 3D Human-Object Interaction

post-thumbnail

8.SELFEXPLAIN: A Self-Explaining Architecture for Neural Text Classifier

post-thumbnail

9.Diffusion Hyperfeatures: Searching Through Time and Space for Semantic Correspondence

post-thumbnail

10.Unsupervised Keypoints from Pretrained Diffusion Model

post-thumbnail

11.Diffuse, Attend, and Segment: Unsupervised Zero-Shot Segmentation using Stable Diffusion

post-thumbnail

12.Object Pose Estimation via the Aggregation of Diffusion Feature

post-thumbnail

13.Hand Pose Estimation via Latent 2.5D Heatmap Regression

post-thumbnail

14.MeshFormer: High-Quality Mesh Generation with 3D-Guided Reconstruction Model

post-thumbnail

15.Structured 3D Latents for Scalable and Versatile 3D Generation

post-thumbnail

16.DINO

post-thumbnail

17.EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything

post-thumbnail

18.ChatPose: Chatting about 3D Human Pose

post-thumbnail

19.CLIP is Also an Efficient Segmenter: A Text-Driven Approach for Weakly Supervised Semantic Segmentation

post-thumbnail

20.3D Gaussian Splatting 강의 정리

post-thumbnail

21.LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation

post-thumbnail

22.DINOv2: Learning Robust Visual Features without Supervision

post-thumbnail

23.Segment Anything

post-thumbnail

26.LangSplat: 3D Language Gaussian Splatting

post-thumbnail

27.EmoTalkingGuassian

post-thumbnail

28.Decoupled Multimodal Distilling for Emotion Recognition

post-thumbnail

29.TalkingGaussian: Structure-Persistent 3D Talking Head Synthesis via Gaussian Splatting

post-thumbnail

30.Enhancing Zero-Shot Facial Expression Recognition by LLM Knowledge Transfer

post-thumbnail

31.EmoVIT: Revolutionizing Emotion Insights with Visual Instruction Tuning

post-thumbnail

32.CocoER: Aligning Multi-Level Feature by Competition and Coordination for Emotion Recognition

post-thumbnail

33.KeyFace: Expressive Audio-Driven Facial Animation for Long Sequences via Key Frame Interpolation

post-thumbnail

34.DREAM-Talk: Diffusion-based Realistic Emotional Audio-driven Method for Single Image Talking Face Generation

post-thumbnail

35.InsTaG: Learning Personalized 3D Talking Head from Few-Second Video

post-thumbnail

36.PERSONA: Personalized Whole-Body 3D Avatar with Pose-Driven Deformations from a Single Image

post-thumbnail

37.RMFER: Semi-supervised Contrastive Learning for Facial Expression Recognition with Reaction Mashup Video

post-thumbnail

38.Contrastive Adversarial Learning for Person Independent Facial Emotion Recognition (AAAI 2021)

post-thumbnail

39.Expressive Whole-Body 3D Gaussian Avatar

post-thumbnail

40.Facial Affective Behavior Analysis with Instruction Tuning (ECCV 2024)

post-thumbnail

41.EDTalk: Efficient Disentanglement for Emotional Talking Head Synthesis (ECCV 2024)

post-thumbnail

42.Progressive Disentangled Representation Learning for Fine-Grained Controllable Talking Head Synthesis (CVPR 2023)

post-thumbnail

43.VTimeLLM: Empower LLM to Grasp Video Moments (CVPR 2024)

post-thumbnail

44.Valence & Arousal Datset 조사 01

post-thumbnail

45.Valence & Arousal Datset 조사 02

post-thumbnail

46.EmoSphere-TTS: Emotional Style and Intensity Modeling via Spherical Emotion Vector for Controllable Emotional Text-to-Speech (Interspeech 2024)

post-thumbnail

47.Emotion LLM 스펙 정리

post-thumbnail

48.Real3D-Portrait: One-shot Realistic 3D Talking Portrait Synthesis (ICLR 2024 Spotlight)

post-thumbnail

49.Can3Tok: Canonical 3D Tokenization and Latent Modeling of Scene-Level 3D Gaussians (CVPR 2025)

post-thumbnail