Image de couverture de livre

StructAlign: Structured Cross-Modal Alignment for Continual Text-to-Video Retrieval

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Wang, Shaokun, Guan, Weili, Han, Jizhou, Wu, Jianlong, Hu, Yupeng, Nie, Liqiang
Format:	Preprint
Publié:	2026
Sujets:	Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

R^3: Composed Video Retrieval via Reasoning-Guided Recalling and Re-ranking
par: Li, Zixu, et autres
Publié: (2026)

The 1st Winner for 5th PVUW MeViS-Text Challenge: Strong MLLMs Meet SAM3 for Referring Video Object Segmentation
par: He, Xusheng, et autres
Publié: (2026)

Advancing Complex Video Object Segmentation via Tracking-Enhanced Prompt: The 1st Winner for 5th PVUW MOSE Challenge
par: Zhang, Jinrong, et autres
Publié: (2026)

Self-Enhanced Image Clustering with Cross-Modal Semantic Consistency
par: Li, Zihan, et autres
Publié: (2025)

OmniEgo-R$^2$: A Routed Reasoning Framework for the 1st Cross-Domain EgoCross Challenge at CVPR 2026
par: Li, Zixu, et autres
Publié: (2026)

TempRet: Temporal Enhancement and Two-Stage Reranking for CVPR 2026 EPIC-KITCHENS-100 Multi-Instance Retrieval Challenge
par: Li, Zixu, et autres
Publié: (2026)

UniCVR: From Alignment to Reranking for Unified Zero-Shot Composed Visual Retrieval
par: Wen, Haokun, et autres
Publié: (2026)

PUMA: Layer-Pruned Language Model for Efficient Unified Multimodal Retrieval with Modality-Adaptive Learning
par: Lyu, Yibo, et autres
Publié: (2025)

Cross-Modal and Uni-Modal Soft-Label Alignment for Image-Text Retrieval
par: Huang, Hailang, et autres
Publié: (2024)

TEMA: Anchor the Image, Follow the Text for Multi-Modification Composed Image Retrieval
par: Li, Zixu, et autres
Publié: (2026)

EgoAdapt: A Multi-Scene Egocentric Adaptation Method for CVPR 2026 HD-EPIC VQA Challenge
par: Chen, Zhiwei, et autres
Publié: (2026)

EgoAction: Egocentric Action Composition with Reliability-Aware Temporal Fusion for the EPIC-KITCHENS Action Detection Challenge at CVPR 2026
par: Fu, Zhiheng, et autres
Publié: (2026)

PersonalAlign: Hierarchical Implicit Intent Alignment for Personalized GUI Agent with Long-Term User-Centric Records
par: Lyu, Yibo, et autres
Publié: (2026)

HUD: Hierarchical Uncertainty-Aware Disambiguation Network for Composed Video Retrieval
par: Chen, Zhiwei, et autres
Publié: (2025)

TCMA: Text-Conditioned Multi-granularity Alignment for Drone Cross-Modal Text-Video Retrieval
par: Zhao, Zixu, et autres
Publié: (2025)

Object-Shot Enhanced Grounding Network for Egocentric Video
par: Feng, Yisen, et autres
Publié: (2025)

GOAL: Geometrically Optimal Alignment for Continual Generalized Category Discovery
par: Han, Jizhou, et autres
Publié: (2026)

Continuous Knowledge-Preserving Decomposition with Adaptive Layer Selection for Few-Shot Class-Incremental Learning
par: Li, Xiaojie, et autres
Publié: (2025)

Spatial Understanding from Videos: Structured Prompts Meet Simulation Data
par: Zhang, Haoyu, et autres
Publié: (2025)

Handling Imbalanced Pseudolabels for Vision-Language Models with Concept Alignment and Confusion-Aware Calibrated Margin
par: Wang, Yuchen, et autres
Publié: (2025)

OFFSET: Segmentation-based Focus Shift Revision for Composed Image Retrieval
par: Chen, Zhiwei, et autres
Publié: (2025)

MoME: Mixture of Multimodal Experts for Generalist Multimodal Large Language Models
par: Shen, Leyang, et autres
Publié: (2024)

Curriculum Coarse-to-Fine Selection for High-IPC Dataset Distillation
par: Chen, Yanda, et autres
Publié: (2025)

Uncovering Hidden Connections: Iterative Search and Reasoning for Video-grounded Dialog
par: Zhang, Haoyu, et autres
Publié: (2023)

ConeSep: Cone-based Robust Noise-Unlearning Compositional Network for Composed Image Retrieval
par: Li, Zixu, et autres
Publié: (2026)

ViSAGE @ NTIRE 2026 Challenge on Video Saliency Prediction
par: Wang, Kun, et autres
Publié: (2026)

Fine-grained Textual Inversion Network for Zero-Shot Composed Image Retrieval
par: Lin, Haoqiang, et autres
Publié: (2025)

Consistent Supervised-Unsupervised Alignment for Generalized Category Discovery
par: Han, Jizhou, et autres
Publié: (2025)

IOTA: Corrective Knowledge-Guided Prompt Learning via Black-White Box Framework
par: Wang, Shaokun, et autres
Publié: (2026)

Multi-Modal Cross-Domain Alignment Network for Video Moment Retrieval
par: Fang, Xiang, et autres
Publié: (2022)

FineCIR: Explicit Parsing of Fine-Grained Modification Semantics for Composed Image Retrieval
par: Li, Zixu, et autres
Publié: (2025)

A Survey on Video Temporal Grounding with Multimodal Large Language Model
par: Wu, Jianlong, et autres
Publié: (2025)

Token-level Correlation-guided Compression for Efficient Multimodal Document Understanding
par: Zhang, Renshan, et autres
Publié: (2024)

ReTaKe: Reducing Temporal and Knowledge Redundancy for Long Video Understanding
par: Wang, Xiao, et autres
Publié: (2024)

Leveraging Modality Tags for Enhanced Cross-Modal Video Retrieval
par: Fragomeni, Adriano, et autres
Publié: (2025)

Video DataFlywheel: Resolving the Impossible Data Trinity in Video-Language Understanding
par: Wang, Xiao, et autres
Publié: (2024)

Decoupled Cross-Modal Alignment Network for Text-RGBT Person Retrieval and A High-Quality Benchmark
par: Deng, Yifei, et autres
Publié: (2025)

AdaReTaKe: Adaptive Redundancy Reduction to Perceive Longer for Video-language Understanding
par: Wang, Xiao, et autres
Publié: (2025)

DecAlign: Hierarchical Cross-Modal Alignment for Decoupled Multimodal Representation Learning
par: Qian, Chengxuan, et autres
Publié: (2025)

AlignGen: Boosting Personalized Image Generation with Cross-Modality Prior Alignment
par: Lin, Yiheng, et autres
Publié: (2025)