IJCV 2024 papers on Vision-language and multimodal
29 of the 343 papers published in IJCV 2024 (8.5%) are on Vision-language and multimodal, compared with 9.1% at IJCV 2023. They fall into 6 topics.
See IJCV 2024 in the interactive map
Working on something in this area? Describe your idea in scime atlas to see the closest papers by meaning and how crowded the spot has become.
Topics and papers
Cross-modal learning · 10 papers
- Audio-Visual Segmentation with Semantics (120 citations)
- Semantic-Aligned Matching for Enhanced DETR Convergence and Multi-Scale Feature Fusion (40 citations)
- CA-MoEiT: Generalizable Face Anti-spoofing via Dual Cross-Attention and Semi-fixed Mixture-of-Expert (38 citations)
- Noise-Resistant Multimodal Transformer for Emotion Recognition (36 citations)
- MutualFormer: Multi-modal Representation Learning via Cross-Diffusion Attention (34 citations)
- Modality-missing RGBT Tracking: Invertible Prompt Learning and High-quality Benchmarks (33 citations)
- Unified Frequency-Assisted Transformer Framework for Detecting and Grounding Multi-modal Manipulation (32 citations)
- Multi-modal Prototypes for Open-World Semantic Segmentation (21 citations)
- Hugs Bring Double Benefits: Unsupervised Cross-Modal Hashing with Multi-granularity Aligned Transformers (19 citations)
- UniMod1K: Towards a More Universal Large-Scale Dataset and Benchmark for Multi-modal Learning (18 citations)
Human and embodied modeling · 8 papers
- LSKNet: A Foundation Lightweight Backbone for Remote Sensing (250 citations)
- An Outlook into the Future of Egocentric Vision (82 citations)
- Deep Learning Technique for Human Parsing: A Survey and Outlook (42 citations)
- Masked Channel Modeling for Bootstrapping Visual Pre-training (6 citations)
- Group-Based Distinctive Image Captioning with Memory Difference Encoding and Attention (3 citations)
- Editor’s Note: Special Issue on Computer Vision Approach for Animal Tracking and Modeling
- Editor’s Note: Special Issue on Computer Vision Approaches for Animal Tracking and Modeling 2023
- Editor’s Note: Special Issue on Robust Vision
CLIP and zero-shot · 7 papers
- Progressive Visual Prompt Learning with Contrastive Feature Re-formation (59 citations)
- WildCLIP: Scene and Animal Attribute Retrieval from Camera Trap Data with Domain-Adapted Vision-Language Models (40 citations)
- I2DFormer+: Learning Image to Document Summary Attention for Zero-Shot Image Classification (34 citations)
- Bi-VLGM: Bi-Level Class-Severity-Aware Vision-Language Graph Matching for Text Guided Medical Image Segmentation (28 citations)
- Open-Vocabulary Animal Keypoint Detection with Semantic-Feature Matching (26 citations)
- Vision-Language Alignment Learning Under Affinity and Divergence Principles for Few-Shot Out-of-Distribution Generalization (17 citations)
- Mutual Prompt Leaning for Vision Language Models (8 citations)
