Continual learning empowers models to adapt autonomously to the ever-changing environment or data streams without forgetting old knowledge. Prompt-based approaches are built on frozen pre-trained models to learn the t...
详细信息
ISBN:
(数字)9798350353006
ISBN:
(纸本)9798350353013
Continual learning empowers models to adapt autonomously to the ever-changing environment or data streams without forgetting old knowledge. Prompt-based approaches are built on frozen pre-trained models to learn the task-specific prompts and classifiers efficiently. Existing prompt-based methods are inconsistent between training and testing, limiting their effectiveness. Two types of inconsistency are revealed. Test predictions are made from all classifiers while training only focuses on the current task classifier without holistic alignment, leading to Classifier inconsistency. Prompt inconsistency indicates that the prompt selected during testing may not correspond to the one associated with this task during training. In this paper, we propose a novel prompt-based method, Consistent Prompting (CPrompt), for more aligned training and testing. Specifically, all existing classifiers are exposed to prompt training, resulting in classifier consistency learning. In addition, prompt consistency learning is proposed to enhance prediction robustness and boost prompt selection accuracy. Our Consistent Prompting surpasses its prompt-based counterparts and achieves state-of-the-art performance on multiple continual learning benchmarks. Detailed analysis shows that improvements come from more consistent training and testing. Our code is available at https://***/Zhanxin-Gao/CPrompt.
We present EgoExo-Fitness, a new full-body action understanding dataset, featuring fitness sequence videos recorded from synchronized egocentric and fixed exocentric (third-person) cameras. Compared with existing full...
详细信息
Spatio-Temporal Video Grounding (STVG) aims to localize the target object spatially and temporally according to the given language query. It is a challenging task in which the model should well understand dynamic visu...
Spatio-Temporal Video Grounding (STVG) aims to localize the target object spatially and temporally according to the given language query. It is a challenging task in which the model should well understand dynamic visual cues (e.g., motions) and static visual cues (e.g., object appearances) in the language description, which requires effective joint modeling of spatiotemporal visuallinguistic dependencies. In this work, we propose a novel framework in which a static vision-language stream and a dynamic vision-language stream are developed to collaboratively reason the target tube. The static stream performs cross-modal understanding in a single frame and learns to attend to the target object spatially according to intraframe visual cues like object appearances. The dynamic stream models visual-linguistic dependencies across multiple consecutive frames to capture dynamic cues like motions. We further design a novel cross-stream collaborative block between the two streams, which enables the static and dynamic streams to transfer useful and complementary information from each other to achieve collaborative reasoning. Experimental results show the effectiveness of the collaboration of the two streams and our overall frame-work achieves new state-of-the-art performance on both HCSTVG and VidSTG datasets.
In this work, we consider the cross-scene person trajectory anomaly detection problem, which detects the anomalous trajectories across multiple nonoverlapping scenes. This problem is highly significant for public secu...
详细信息
The poor prognosis of triple-negative breast cancer(TNBC)results from its high metastasis,whereas inflammation accompanied by excessive reactive oxygen species(ROS)is prone to aggravate tumor *** photothermal therapy(...
详细信息
The poor prognosis of triple-negative breast cancer(TNBC)results from its high metastasis,whereas inflammation accompanied by excessive reactive oxygen species(ROS)is prone to aggravate tumor *** photothermal therapy(PTT)has extremely high therapeutic efficiency,the crafty tumor cells allow an increase in the expression of heat shock proteins(HSPs)to limit its effect,and PTT-induced inflammation is also thought to be a potential trigger for tumor ***,myricetin,iron ions,and polyvinylpyrrolidone were utilized to develop nanomedicines by self-assembly strategy for the treatment of metastatic *** nanomedicines with marvelous water solubility and dispersion can inhibit glucose transporter 1 and interfere with mitochondrial function to block the energy supply of tumor cells,achieving starvation therapy on TNBC *** with excellent photothermal conversion properties allow down-regulating the expression of HSPs to enhance the effect of ***,the broad spectrum of ROS scavenging ability of nanomedicines successfully attenuates PTT-induced inflammation as well as influences hypoxia-inducible factors-1α/3-phosphoinositide-dependent protein kinase 1 related pathway through glycometabolism inhibition to reduce tumor cell ***,the nanomedicines have negligible side effects and good clinical application prospects,which provides a valuable paradigm for the treatment of metastatic TNBC through glycometabolism interference,anti-inflammation,starvation,and photothermal synergistic therapy.
Emotion is a complex phenomenon that greatly affects human behavior and thinking in daily life. Electroencephalography (EEG), one of the human physiological signals, has been emphasized by most researchers in emotion ...
Emotion is a complex phenomenon that greatly affects human behavior and thinking in daily life. Electroencephalography (EEG), one of the human physiological signals, has been emphasized by most researchers in emotion recognition as its specific properties are closely associated with human emotion. However, the number of human emotion recognition studies using computer games as stimuli is still insufficient as there were no relevant publicly available datasets provided in the past decades. Most of the recent studies using the Gameemo public dataset have not clarified the relationship between the EEG signal’s changes and the emotion elicited using computer games. Thus, this paper is proposed to introduce the use of data mining techniques in investigating the relationships between the frequency changes of EEG signals and the human emotion elicited when playing different kinds of computer games. The data acquisition stage, data pre-processing, data annotation and feature extraction stage were designed and conducted in this paper to obtain and extract the EEG features from the Gameemo dataset. The cross-subject and subject-based experiments were conducted to evaluate the classifiers’ performance. The top 10 association rules generated by the RCAR classifier will be examined to determine the possible relationship between the EEG signal's frequency changes and game-induced emotions. The RCAR classifier constructed for cross-subject experiment achieved highest accuracy, precision, recall and F1-score evaluated with over 90% in classifying the HAPV, HANV and LANV game-induced emotions. The 20 experiment cases’ results from subject-based experiments supported that the SVM classifier could accurately classify the 4 emotion states with a kappa value over 0.62, demonstrating the SVM-based algorithm’s capabilities in precisely determining the emotion label for each participant’s EEG features’ instance. The findings in this study fill the existing gap of game-induced emotion recog
In this work, we explore a novel task of generating human grasps based on single-view scene point clouds, which more accurately mirrors the typical real-world situation of observing objects from a single viewpoint. Du...
详细信息
Magnetorheological (MR) rotary brakes leverage the magnetically controllable rheological properties of MR fluids to provide damping torque in lower limb assistance devices. This paper utilizes an optimization algorith...
详细信息
Artificial intelligence methods offer objectivity and convenience in automatic depression detection, however, current research often neglects the critical role of facial landmarks. This oversight results in insufficie...
详细信息
Brain-computer interface (BCI) is a kind of human-computer interaction which can realize the communication and control between human brain and the external environment. The single-modality BCI has the problems of smal...
详细信息
暂无评论