Related papers: MoCrop: Training Free Motion Guided Cropping for E…
State-of-the-art video-text retrieval (VTR) methods typically involve fully fine-tuning a pre-trained model (e.g. CLIP) on specific datasets. However, this can result in significant storage costs in practical applications as a separate…
The well-aligned attribute of CLIP-based models enables its effective application like CLIPscore as a widely adopted image quality assessment metric. However, such a CLIP-based metric is vulnerable for its delicate multimodal alignment. In…
We present a method for gesture detection and localisation based on multi-scale and multi-modal deep learning. Each visual modality captures spatial information at a particular spatial scale (such as motion of the upper body or a hand), and…
Dense self-supervised learning has shown great promise for learning pixel- and patch-level representations, but extending it to videos remains challenging due to the complexity of motion dynamics. Existing approaches struggle as they rely…
We propose a webly-supervised representation learning method that does not suffer from the annotation unscalability of supervised learning, nor the computation unscalability of self-supervised learning. Most existing works on…
Generating motion-controlled videos--where user-specified actions drive physically plausible scene dynamics under freely chosen viewpoints--demands two capabilities: (1) disentangled motion control, allowing users to separately control the…
This paper presents MEMROC (Multi-Eye to Mobile RObot Calibration), a novel motion-based calibration method that simplifies the process of accurately calibrating multiple cameras relative to a mobile robot's reference frame. MEMROC utilizes…
Vision-language retrieval is an important multi-modal learning topic, where the goal is to retrieve the most relevant visual candidate for a given text query. Recently, pre-trained models, e.g., CLIP, show great potential on retrieval…
The availability of city-scale Lidar maps enables the potential of city-scale place recognition using mobile cameras. However, the city-scale Lidar maps generally need to be compressed for storage efficiency, which increases the difficulty…
Motion-based controllable video generation offers the potential for creating captivating visual content. Existing methods typically necessitate model training to encode particular motion cues or incorporate fine-tuning to inject certain…
Conventionally, spatiotemporal modeling network and its complexity are the two most concentrated research topics in video action recognition. Existing state-of-the-art methods have achieved excellent accuracy regardless of the complexity…
CLIP has demonstrated strong generalization in visual domains through natural language supervision, even for video action recognition. However, most existing approaches that adapt CLIP for action recognition have primarily focused on…
We present MotionCrafter, a framework that leverages video generators to jointly reconstruct 4D geometry and estimate dense motion from a monocular video. The key idea is a joint representation of dense 3D point maps and 3D scene flows in a…
The quality of the image representations obtained from self-supervised learning depends strongly on the type of data augmentations used in the learning formulation. Recent papers have ported these methods from still images to videos and…
Image-to-video generation has made remarkable progress with the advancements in diffusion models, yet generating videos with realistic motion remains highly challenging. This difficulty arises from the complexity of accurately modeling…
Recent adaptations can boost the low-shot capability of Contrastive Vision-Language Pre-training (CLIP) by effectively facilitating knowledge transfer. However, these adaptation methods are usually operated on the global view of an input…
Segmentation of moving objects in dynamic scenes is a key process in scene understanding for navigation tasks. Classical cameras suffer from motion blur in such scenarios rendering them effete. On the contrary, event cameras, because of…
The main challenge of Multi-Object Tracking~(MOT) lies in maintaining a continuous trajectory for each target. Existing methods often learn reliable motion patterns to match the same target between adjacent frames and discriminative…
Few-shot, fine-grained classification in computer vision poses significant challenges due to the need to differentiate subtle class distinctions with limited data. This paper presents a novel method that enhances the Contrastive…
Mobile video analysis systems often encounter various deploying environments, where environment shifts present greater demands for responsiveness in adaptations of deployed "expert DNN models". Existing model adaptation frameworks primarily…