alipay / PC2-NoiseofWebLinks
Noise of Web (NoW) is a challenging noisy correspondence learning (NCL) benchmark containing 100K image-text pairs for robust image-text matching/retrieval models.
☆15Updated last month
Alternatives and similar repositories for PC2-NoiseofWeb
Users that are interested in PC2-NoiseofWeb are comparing it to the libraries listed below
Sorting:
- 【ICLR 2024, Spotlight】Sentence-level Prompts Benefit Composed Image Retrieval☆87Updated last year
- [CVPR 2024] Context-Guided Spatio-Temporal Video Grounding☆58Updated last year
- FreeVA: Offline MLLM as Training-Free Video Assistant☆63Updated last year
- [ICLR 2025] TRACE: Temporal Grounding Video LLM via Casual Event Modeling☆126Updated last month
- [ICLR 2025] TimeSuite: Improving MLLMs for Long Video Understanding via Grounded Tuning☆45Updated 6 months ago
- [BMVC 2023] Zero-shot Composed Text-Image Retrieval☆54Updated 10 months ago
- Can I Trust Your Answer? Visually Grounded Video Question Answering (CVPR'24, Highlight)☆80Updated last year
- ☆80Updated 10 months ago
- The official code of Towards Balanced Alignment: Modal-Enhanced Semantic Modeling for Video Moment Retrieval (AAAI2024)☆31Updated last year
- [CVPR 2024] Do you remember? Dense Video Captioning with Cross-Modal Memory Retrieval☆59Updated last year
- Official PyTorch code of GroundVQA (CVPR'24)☆62Updated last year
- Official implementation of HawkEye: Training Video-Text LLMs for Grounding Text in Videos☆42Updated last year
- [CVPR 2023 Highlight & TPAMI] Video-Text as Game Players: Hierarchical Banzhaf Interaction for Cross-Modal Representation Learning☆122Updated 9 months ago
- Context-I2W: Mapping Images to Context-dependent words for Accurate Zero-Shot Composed Image Retrieval [AAAI 2024 Oral]☆55Updated 4 months ago
- [IJCAI 2023] Text-Video Retrieval with Disentangled Conceptualization and Set-to-Set Alignment☆53Updated last year
- Official Implementation (Pytorch) of the "VidChain: Chain-of-Tasks with Metric-based Direct Preference Optimization for Dense Video Capti…☆22Updated 8 months ago
- Composed Video Retrieval☆61Updated last year
- Code for DeCo: Decoupling token compression from semanchc abstraction in multimodal large language models☆71Updated 2 months ago
- This is the official implementation of ReVisionLLM: Recursive Vision-Language Model for Temporal Grounding in Hour-Long Videos☆29Updated 3 months ago
- ☆20Updated 2 months ago
- Reinforcement Learning Tuning for VideoLLMs: Reward Design and Data Efficiency☆54Updated 4 months ago
- A Versatile Video-LLM for Long and Short Video Understanding with Superior Temporal Localization Ability☆98Updated 10 months ago
- Code implementation of paper "MUSE: Mamba is Efficient Multi-scale Learner for Text-video Retrieval (AAAI2025)"☆22Updated 8 months ago
- Official implementation of CVPR 2024 paper "vid-TLDR: Training Free Token merging for Light-weight Video Transformer".☆52Updated last year
- Emerging Pixel Grounding in Large Multimodal Models Without Grounding Supervision☆40Updated 6 months ago
- Mitigating Shortcuts in Visual Reasoning with Reinforcement Learning☆37Updated 3 months ago
- [AAAI 2024] GMMFormer: Gaussian-Mixture-Model Based Transformer for Efficient Partially Relevant Video Retrieval☆18Updated last year
- MMICL, a state-of-the-art VLM with the in context learning ability from ICL, PKU☆50Updated 2 months ago
- [ECCV2024] Reflective Instruction Tuning: Mitigating Hallucinations in Large Vision-Language Models☆18Updated last year
- [ECCV 2024] Learning Video Context as Interleaved Multimodal Sequences☆40Updated 7 months ago