Related papers: Unmasked Teacher: Towards Training-Efficient Video…
Video-based pretraining offers immense potential for learning strong visual representations on an unprecedented scale. Recently, masked video modeling methods have shown promising scalability, yet fall short in capturing higher-level…
Masked Autoencoders (MAEs) learn generalizable representations for image, text, audio, video, etc., by reconstructing masked input data from tokens of the visible data. Current MAE approaches for videos rely on random patch, tube, or…
To build scalable models for challenging real-world tasks, it is important to learn from diverse, multi-modal data in various forms (e.g., videos, text, and images). Among the existing works, a plethora of them have focused on leveraging…
Recent advancements in video saliency prediction (VSP) have shown promising performance compared to the human visual system, whose emulation is the primary goal of VSP. However, current state-of-the-art models employ spatio-temporal…
Learning with large-scale unlabeled data has become a powerful tool for pre-training Visual Transformers (VTs). However, prior works tend to overlook that, in real-world scenarios, the input data may be corrupted and unreliable.…
Recent studies reveal that integrating new modalities into Large Language Models (LLMs), such as Vision-Language Models (VLMs), creates a new attack surface that bypasses existing safety training techniques like Supervised Fine-tuning (SFT)…
Video-Language Models (VLMs) have demonstrated impressive multi-modal reasoning capabilities across diverse computer vision applications. However, these VLMs are task-specific and assume that both video and language inputs are complete.…
Unlike natural language processing and computer vision, the development of Foundation Models (FMs) for time series forecasting is blocked due to data scarcity. While recent efforts are focused on building such FMs by unlocking the potential…
Deep video recognition is more computationally expensive than image recognition, especially on large-scale datasets like Kinetics [1]. Therefore, training scalability is essential to handle a large amount of videos. In this paper, we study…
Recent studies have indicated that vision models pre-trained on images can serve as time series foundation models (TSFMs) by reformulating time series forecasting (TSF) as image reconstruction. However, effective cross-modal transfer from…
Vision-language pre-training (VLP) methods are blossoming recently, and its crucial goal is to jointly learn visual and textual features via a transformer-based architecture, demonstrating promising improvements on a variety of…
Most existing vision-language pre-training methods focus on understanding tasks and use BERT-like objectives (masked language modeling and image-text matching) during pretraining. Although they perform well in many understanding downstream…
With abundant, unlabeled real faces, how can we learn robust and transferable facial representations to boost generalization across various face security tasks? We make the first attempt and propose FS-VFM, a scalable self-supervised…
Recently, vision transformer (ViT) based multimodal learning methods have been proposed to improve the robustness of face anti-spoofing (FAS) systems. However, there are still no works to explore the fundamental natures (\textit{e.g.},…
Effective spatiotemporal feature representation is crucial to the video-based action recognition task. Focusing on discriminate spatiotemporal feature learning, we propose Information Fused Temporal Transformation Network (IF-TTN) for…
Training on large-scale datasets can boost the performance of video instance segmentation while the annotated datasets for VIS are hard to scale up due to the high labor cost. What we possess are numerous isolated filed-specific datasets,…
Fine-grained alignment between videos and text is challenging due to complex spatial and temporal dynamics in videos. Existing video-based Large Multimodal Models (LMMs) handle basic conversations but struggle with precise pixel-level…
Unifying diverse image generation tasks within a single framework remains a fundamental challenge in visual generation. While large language models (LLMs) achieve unification through task-agnostic data and generation, existing visual…
Although Video Large Language Models (VLLMs) have shown remarkable capabilities in video understanding, they are required to process high volumes of visual tokens, causing significant computational inefficiency. Existing VLLMs acceleration…
We present Recurrent Video Masked-Autoencoders (RVM): a novel approach to video representation learning that leverages recurrent computation to model the temporal structure of video data. RVM couples an asymmetric masking objective with a…