Related papers: MEGA: Multimodal Alignment Aggregation and Distill…
The proliferation of online short video platforms has driven a surge in user demand for short video editing. However, manually selecting, cropping, and assembling raw footage into a coherent, high-quality video remains laborious and…
Self-supervised audio-visual source separation leverages natural correlations between audio and vision modalities to separate mixed audio signals. In this work, we first systematically analyse the performance of existing multimodal fusion…
Most existing real-time deep models trained with each frame independently may produce inconsistent results across the temporal axis when tested on a video sequence. A few methods take the correlations in the video sequence into…
In this work, we propose an efficient Video-Language Alignment (ViLA) network. Our ViLA model addresses both efficient frame sampling and effective cross-modal alignment in a unified way. In our ViLA network, we design a new learnable…
Recently, learning open-vocabulary semantic segmentation from text supervision has achieved promising downstream performance. Nevertheless, current approaches encounter an alignment granularity gap owing to the absence of dense annotations,…
Image diffusion distillation achieves high-fidelity generation with very few sampling steps. However, applying these techniques directly to video diffusion often results in unsatisfactory frame quality due to the limited visual quality in…
Scene, as the crucial unit of storytelling in movies, contains complex activities of actors and their interactions in a physical environment. Identifying the composition of scenes serves as a critical step towards semantic understanding of…
Text-video retrieval aims to find the most relevant cross-modal samples for a given query. Recent methods focus on modeling the whole spatial-temporal relations. However, since video clips contain more diverse content than captions, the…
Video synthesis has recently made remarkable strides benefiting from the rapid development of diffusion models. However, it still encounters challenges in terms of semantic accuracy, clarity and spatio-temporal continuity. They primarily…
Video data is increasingly used alongside conventional data for interactive data exploration, necessitating interfaces for exploring and presenting mixed-modality data. However, integrating video into visualizations remains difficult due to…
Dataset distillation has demonstrated remarkable effectiveness in high-compression scenarios for image datasets. While video datasets inherently contain greater redundancy, existing video dataset distillation methods primarily focus on…
We propose Compressed Video Aggregator (CVA), a lightweight micro-video recommendation module that decouples video information from preference learning. It aggregates frozen VFM embeddings, and uses latent reasoning without cross-attention…
In the era of large-scale pre-trained models, effectively adapting general knowledge to specific affective computing tasks remains a challenge, particularly regarding computational efficiency and multimodal heterogeneity. While…
Multimodal learning has gained much success in recent years. However, current multimodal fusion methods adopt the attention mechanism of Transformers to implicitly learn the underlying correlation of multimodal features. As a result, the…
Multimodal alignment is commonly learned from isolated image-text pairs via CLIP-style dual encoders, leaving the relational context among entities largely unused. Multimodal attributed graphs (MAGs), where nodes carry multimodal attributes…
Event cameras have the potential to revolutionize the field of robot vision, particularly in areas like stereo disparity estimation, owing to their high temporal resolution and high dynamic range. Many studies use deep learning for event…
A key challenge in synthesizing audios from silent videos is the inherent trade-off between synthesis quality and inference efficiency in existing methods. For instance, flow matching based models rely on modeling instantaneous velocity,…
Real-time computational speed and a high degree of precision are requirements for computer-assisted interventions. Applying a segmentation network to a medical video processing task can introduce significant inter-frame prediction noise.…
Weakly-supervised action segmentation is a task of learning to partition a long video into several action segments, where training videos are only accompanied by transcripts (ordered list of actions). Most of existing methods need to infer…
Temporal modeling is key for action recognition in videos. It normally considers both short-range motions and long-range aggregations. In this paper, we propose a Temporal Excitation and Aggregation (TEA) block, including a motion…