Crossclr: Cross-modal Contrastive Learning For Multi-modal Video Representations

Abstract

Contrastive learning allows us to flexibly define powerful losses by contrasting positive pairs from sets of negative samples. Recently, the principle has also been used to learn cross-modal embeddings for video and text, yet without exploiting its full potential. In particular, previous losses do not take the intra-modality similarities into account, which leads to inefficient embeddings, as the same content is mapped to multiple points in the embedding space. With CrossCLR, we present a contrastive loss that fixes this issue. Moreover, we define sets of highly related samples in terms of their input embeddings and exclude them from the negative samples to avoid issues with false negatives. We show that these principles consistently improve the quality of the learned embeddings. The joint embeddings learned with CrossCLR extend the state of the art in video-text retrieval on Youcook2 and LSMDC datasets and in video captioning on Youcook2 dataset by a large margin. We also demonstrate

Stats

• citations119
• S2 citations—
• github stars0
• HF likes0
• heat score15.59
• arxiv keyzolfaghari2021crossclr

Related papers

• MXM-CLR: A Unified Framework For Contrastive Learning Of Multifold Cross-modal Representations (2023)0.00
• X-CLIP: End-to-end Multi-grained Contrastive Learning For Video-text Retrieval (2022)18.12
• Normalized Contrastive Learning For Text-video Retrieval (2022)6.77
• Contrastive Learning Of Visual-semantic Embeddings (2021)0.00
• Cross The Gap: Exposing The Intra-modal Misalignment In CLIP Via Modality Inversion (2025)3.64
• Robust Cross-modal Representation Learning With Progressive Self-distillation (2022)12.33
• Generalized Contrastive Learning For Universal Multimodal Retrieval (2025)0.00
• Contrastive Video-language Learning With Fine-grained Frame Sampling (2022)6.77