Related papers: MoCrop: Training Free Motion Guided Cropping for E…
Multi-object tracking (MOT) at low frame rates can reduce computational, storage and power overhead to better meet the constraints of edge devices. Many existing MOT methods suffer from significant performance degradation in low-frame-rate…
High frame-rate (HFR) videos of action recognition improve fine-grained expression while reducing the spatio-temporal relation and motion information density. Thus, large amounts of video samples are continuously required for traditional…
This paper describes AutoFocus, an efficient multi-scale inference algorithm for deep-learning based object detectors. Instead of processing an entire image pyramid, AutoFocus adopts a coarse to fine approach and only processes regions…
Recent vision-language models excel at large-scale image-text alignment but often neglect the compositional structure of language, leading to failures on tasks that hinge on word order and predicate-argument structure. We introduce…
We introduce MoMa, a novel modality-aware mixture-of-experts (MoE) architecture designed for pre-training mixed-modal, early-fusion language models. MoMa processes images and text in arbitrary sequences by dividing expert modules into…
Pre-trained vision-language (V-L) models such as CLIP have shown excellent generalization ability to downstream tasks. However, they are sensitive to the choice of input text prompts and require careful selection of prompt templates to…
We present MOFA-Video, an advanced controllable image animation method that generates video from the given image using various additional controllable signals (such as human landmarks reference, manual trajectories, and another even…
Object detection, one of the three main tasks of computer vision, has been used in various applications. The main process is to use deep neural networks to extract the features of an image and then use the features to identify the class and…
So far, efficient fine-tuning has become a popular strategy for enhancing the capabilities of foundation models on downstream tasks by learning plug-and-play modules. However, existing methods overlook a crucial issue: if the underlying…
Adaptive robotics plays an essential role in achieving truly co-creative cyber physical systems. In robotic manipulation tasks, one of the biggest challenges is to estimate the pose of given workpieces. Even though the recent…
Eliminating image blur produced by various kinds of motion has been a challenging problem. Dominant approaches rely heavily on model capacity to remove blurring by reconstructing residual from blurry observation in feature space. These…
Optical motion capture is a foundational technology driving advancements in cutting-edge fields such as virtual reality and film production. However, system performance suffers severely under large-scale marker occlusions common in…
Large pre-trained vision-language models, such as CLIP, have demonstrated state-of-the-art performance across a wide range of image classification tasks, without requiring retraining. Few-shot CLIP is competitive with existing specialized…
Field-captured video facilitates detailed studies of spatio-temporal aspects of animal locomotion, decision-making and environmental interactions including predator-prey relationships and habitat utilisation. But even though data capture is…
Untrimmed videos on social media or those captured by robots and surveillance cameras are of varied aspect ratios. However, 3D CNNs usually require as input a square-shaped video, whose spatial dimension is smaller than the original.…
Adaptive sampling that exploits the spatiotemporal redundancy in videos is critical for always-on action recognition on wearable devices with limited computing and battery resources. The commonly used fixed sampling strategy is not…
The existing action tubelet detectors often depend on heuristic anchor design and placement, which might be computationally expensive and sub-optimal for precise localization. In this paper, we present a conceptually simple, computationally…
Recent advancements in multimodal foundation models (e.g., CLIP) have excelled in zero-shot generalization. Prompt tuning involved in the knowledge transfer from foundation models to downstream tasks has gained significant attention…
This paper aims at addressing the problem of substantial performance degradation at extremely low computational cost (e.g. 5M FLOPs on ImageNet classification). We found that two factors, sparse connectivity and dynamic activation function,…
Multi-object tracking (MOT) is critical in numerous real-world applications, including surveillance, autonomous driving, and robotics. Accurately predicting object motion is fundamental to MOT, but current methods struggle with the…