Deep polyp segmentation methods have shown remarkable potential in boosting diagnostic efficiency. Nevertheless, these methods rely on sufficient pixel-wise annotated data, which is time-consuming and labor-intensive to acquire in clinical practice. This challenge is further escalated under the polyp segmentation scenario due to the massive video frames. To alleviate annotating burden, in this letter, we propose a label-efficient polyp segmentation framework named HybridVPS, which drastically reduces the annotation cost while maintaining satisfactory performance. Our core insight is to take full advantage of the similar semantics between consecutive video frames. Specifically, only a few frames require pixel-wise annotations, while the cheap scribble annotations are enough for the remaining part. To fully leverage the coarse location information provided by scribble annotations, we introduce an adaptive label prompter, which utilizes pixel-wise annotation to provide reliable guidance for scribble-annotated neighboring frames, thus facilitating the overall accuracy of the segmentation. Extensive experiments on the large-scale video polyp dataset SUN-SEG demonstrate the superiority of our approach. HybridVPS achieves comparable performance to the fully supervised scheme while requiring only 2% of the pixel-level annotations.

Currently, there is a growing scholarly and industrial interest in micro-video-centric research. Within these domains, multi-label learning has emerged as a fundamental yet attractive subject. Existing methods primarily place emphasis on feature representations of individual micro-videos, while neglecting latent interdependencies between instance and label domains. To address this problem, in this paper, we propose a novel self-attentive deep consistent matrix factorization (SADCMF) method, which jointly explores dualdomain hierarchical representations and their inherent dependencies for micro-video multi-label classification. Specifically, SADCMF includes three primary characteristics: 1) A dualdomain deep collaborative factorization module is developed to explore the first-stage representations of instance features and the discriminative embeddings of label semantics in a mutually beneficial manner. 2) A correlation-driven selfattentive factorization module is devised to acquire the labelaware attentive outputs, which are further combined with original features through a residual structure to enrich the second-stage feature representations. 3) A dual-stream representation consistency module ensures the unidirectional and bidirectional representation consistency, meanwhile, narrows the discrepancies between the two-stage representations for improving the generalization ability of our method. Extensive experiments conducted on two publicly available micro-video multi-label datasets demonstrate its superior performance in comparison with state-of-the-art methods.

Recently, with the growing popularity of micro-videos, multi-label learning has attracted increasing attention due to its potential commercial value in different scenarios. However, existing methods place more emphasis on the alignment between explicit semantics and visual features, while neglecting the exploration of interactions at fine-grained semantic levels. To address this problem, we propose a novel dual-domain aligned deep hierarchical matrix factorization (DADHMF) method for micro-video multi-label classification. Specifically, we construct a dual-stream deep matrix factorization framework to explore implicit hierarchical semantics and corresponding intrinsic feature representations in top-down and bottom-up ways, respectively. On this basis, we leverage the intralayer alignment strategy to narrow the semantic gap between label and instance domains by introducing adaptive semantic-aware embeddings. Moreover, we further utilize the inverse covariance estimation module to automatically capture latent semantic correlations, and project the structural information into the semantic-aware embeddings to ensure the stability of the intralayer alignment. Extensive experiments on two available micro-video multi-label datasets demonstrate that our proposed method outperforms the state-of-the-art methods.

Micro-videos, as an increasingly popular form of user-generated content (UGC), naturally include diverse multimodal cues. However, in pursuit of consistent representations, existing methods neglect the simultaneous consideration of exploring modality discrepancy and preserving modality diversity. In this paper, we propose a multimodal progressive modulation network (MPMNet) for micro-video multi-label classification, which enhances the indicative ability of each modality through gradually regulating various modality biases. In MPMNet, we first leverage a unimodal-centered parallel aggregation strategy to obtain preliminary comprehensive representations. We then integrate feature-domain disentangled modulation process and category-domain adaptive modulation process into a unified framework to jointly refine modality-oriented representations. In the former modulation process, we constrain inter-modal dependencies in a latent space to obtain modality-oriented sample representations, and introduce a disentangled paradigm to further maintain modality diversity. In the latter modulation process, we construct global-context-aware graph convolutional networks to acquire modality-oriented category representations, and develop two instance-level parameter generators to further regulate unimodal semantic biases. Extensive experiments on two micro-video multi-label datasets show that our proposed approach outperforms the state-of-the-art methods.

Channel pruning facilitates the acceleration and deployment of convolutional neural networks on resource-constrained devices. Nevertheless, existing related methods mainly focus on the importance of an individual channel, neglecting the intra-layer relationship and inter-layer influence. In this paper, we propose a novel local attention and global ranking (LAGR) method for channel pruning. Specifically, we first introduce the attention mechanism to explore the local correlation between channels of the intra-layer. On this basis, we evaluate the global ranking of all channels across the network by the normalization operation. Besides, we introduce a noisy training strategy in the pre-training stage to ensure a balanced weight distribution. Extensive experiments conducted on three representative networks, including VGGNet, GoogLeNet, and ResNet, have demonstrated the superior performance of the proposed method in comparison with several state-of-the-art methods.

Filter pruning has attracted increasing attentions to compress and accelerate the convolutional neural networks (CNNs) on computationally restricted devices. Existing related methods mainly focus on independently leveraging the spatial information of individual filters while ignoring the inner correlation among filters. In this letter, we propose a dual rank-constrained filter pruning approach for convolutional neural networks, in which the representation, clustering, and identification of representative filters are integrated into an adaptive graph regularization framework. Particularly, the proposed approach utilizes the low-rank constraint to capture the low-dimensional intrinsic representations of filters for the adaptive affinity graph construction and clustering. It is noteworthy that the original filters are projected as points on Grassmann manifold for geometrical structure preserving. Meanwhile, the high-rank constraint is employed to select the most informative filter for representing the cluster. Experimental results on CIFAR-10 dataset show that the proposed approach achieves competitive results compared with the state-of-the-art methods by 87.1% in VGGNet-16, 52.4% in GoogLeNet and 72.9% in ResNet-56 in terms of model parameters compression.

With the rapid development of the wireless sensor network and the continuous improvement of its key technologies, the concept of Internet of Things has been encouraged and extended due to its wide applications in scenarios, such as smart homes and healthcare. Under the background, human activity recognition has drawn great attention in recent years. In this paper, we present a discriminant approach to recognize daily human activities recorded through accelerometer sensor. In the proposed approach, we first use S transform (ST) to extract features, and then introduce a supervised regularization-based robust subspace (SRRS) learning method to learn low-dimensional intrinsic feature representation from the original feature subspace. Particularly, ST has been described as a joint time-frequency representation, which is insensitive to noise. SRRS can learn more robust and discriminative features to reinforce the descriptions of samples while removing noise and redundancy. Experiments are conducted on three publicly available datasets, i.e., wireless sensor data mining, SCUT-NAA, and mHealth demonstrating the superior performance of our proposed scheme compared with state-of-the-art methods.