Multi-source transfer learning provides an effective solution to data scarcity in real-world supervised learning scenarios by leveraging multiple source tasks. In this field, existing works typically use all available samples from sources in training, which constrains their training efficiency and may lead to suboptimal results. To address this, we propose a theoretical framework that answers the question: what is the optimal quantity of source samples needed from each source task to jointly train the target model? Specifically, we introduce a generalization error measure based on K-L divergence, and minimize it based on high-dimensional statistical analysis to determine the optimal transfer quantity for each source task. Additionally, we develop an architecture-agnostic and data-efficient algorithm OTQMS to implement our theoretical results for target model training in multi-source transfer learning. Experimental studies on diverse architectures and two real-world benchmark datasets show that our proposed algorithm significantly outperforms state-of-the-art approaches in both accuracy and data efficiency. The code is available at https://github.com/zqy0126/OTQMS.

This paper studies the spatio-temporal video grounding task, which aims to localize a spatio-temporal tube in an untrimmed video based on the given text description of an event. Existing one-stage approaches suffer from insufficient space-time interaction in two aspects: i) less precise prediction of event temporal boundaries, and ii) inconsistency in object prediction for the same event across adjacent frames. To address these issues, we propose a framework of Comprehensive Space-Time entAnglement (CoSTA) to densely entangle space-time multi-modal features for spatio-temporal localization. Specifically, we propose a space-time collaborative encoder to extract comprehensive video features and leverage Transformer to perform spatio-temporal multi-modal understanding. Our entangled decoder couples temporal boundary prediction and spatial localization via an entangled query, boasting an enhanced ability to capture object-event relationships. We conduct extensive experiments on the challenging benchmarks of HC-STVG and VidSTG, where CoSTA outperforms existing state-of-the-art methods, demonstrating its effectiveness for this task.

Video grounding aims to localize the target moment in an untrimmed video corresponding to a given sentence query. Existing methods typically select the best prediction from a set of predefined proposals or directly regress the target span in a single-shot manner, resulting in the absence of a systematical and well-crafted prediction refinement process. In this paper, we propose DiffusionVG, a novel framework with diffusion models that formulates video grounding as a conditional generative task, where the target span is generated from Gaussian noise inputs and iteratively refined in the reverse diffusion process. During training, Diffusion VG progressively adds noise to the target span with a fixed forward diffusion process and learns to recover the target span in the reverse diffusion process. In inference, Diffusion VG can effectively generate the target span from Gaussian noise inputs by the learned reverse diffusion process conditioned on the video-sentence representations. Without bells and whistles, our DiffusionVG demonstrates superior performance compared to existing state-of-the-art methods on mainstream Charades-STA, ActivityNet Captions, and TACoS benchmarks.

Dependency structures between modalities have been utilized explicitly and implicitly in multimodal learning to enhance classification performance, particularly when the training samples are insufficient. Recent efforts have con-centrated on developing mathematical frameworks utilizing conditional dependency structures, but the non-asymptotic relations between the training sample size and various structures are not sufficiently addressed. To address this issue, we propose a mathematical framework that can be utilized to characterize conditional dependency structures in analytic ways. It provides an explicit description of the sample size in learning various structures in a non-asymptotic regime. Additionally, it demonstrates how task complexity and a fitness evaluation of conditional dependence structures affect the results. Furthermore, we develop an autonomously updated coefficient algorithm auto-CODES based on the theoretical framework and conduct experiments on multimodal emotion recognition tasks using the MELD dataset. The experimental results validate our theory and show the effectiveness of the proposed algorithm.

The Multi-modal Large Language Model (MLLM) based Referring Expression Generation (REG) task has gained increasing popularity, which aims to generate an unambiguous text description that applies to exactly one object or region in the image by leveraging foundation models. We empirically found that there exists a potential trade-off between the detailedness and the correctness of the descriptions for the referring objects. On the one hand, generating sentences with more details is usually required in order to provide more precise object descriptions. On the other hand, complicated sentences could easily increase the probability of hallucinations. To address this issue, we propose a training-free framework, named ``unleash-then-eliminate'', which first elicits the latent information in the intermediate layers, and then adopts a cycle-consistency-based decoding method to alleviate the production of hallucinations. Furthermore, to reduce the computational load of cycle-consistency-based decoding, we devise a Probing-based Importance Estimation method to statistically estimate the importance weights of intermediate layers within a subset. These importance weights are then incorporated into the decoding process over the entire dataset, intervening in the next token prediction from intermediate layers. Extensive experiments conducted on the RefCOCOg and PHD benchmarks show that our proposed framework could outperform existing methods on both semantic and hallucination-related metrics. Code will be made available in https://github.com/Glupayy/unleash-eliminate.

In this paper, we study the problem of visual grounding by considering both phrase extraction and grounding (PEG). In contrast to the previous phrase-known-at-test setting, PEG requires a model to extract phrases from text and locate objects from image simultaneously, which is a more practical setting in real applications. As phrase extraction can be regarded as a 1D text segmentation problem, we formulate PEG as a dual detection problem and propose a novel DQ-DETR model, which introduces dual queries to probe different features from image and text for object prediction and phrase mask prediction. Each pair of dual queries are designed to have shared positional parts but different content parts. Such a design effectively alleviates the difficulty of modality alignment between image and text (in contrast to a single query design) and empowers Transformer decoder to leverage phrase mask-guided attention to improve the performance. To evaluate the performance of PEG, we also propose a new metric CMAP (cross-modal average precision), analogous to the AP metric in object detection. The new metric overcomes the ambiguity of Recall@1 in many-box-to-one-phrase cases in phrase grounding. As a result, our PEG pre-trained DQ-DETR establishes new state-of-the-art results on all visual grounding benchmarks with a ResNet-101 backbone. For example, it achieves 91.04% and 83.51% in terms of recall rate on RefCOCO testA and testB with a ResNet-101 backbone.

In this paper, we introduce a novel approach to novel object captioning which employs relative contrastive learning to learn visual and semantic alignment. Our approach maximizes compatibility between regions and object tags in a contrastive manner. To set up a proper contrastive learning objective, for each image, we augment tags by leveraging the relative nature of positive and negative pairs obtained from foundation models such as CLIP. We then use the rank of each augmented tag in a list as a relative relevance label to contrast each top-ranked tag with a set of lower-ranked tags. This learning objective encourages the top-ranked tags to be more compatible with their image and text context than lower-ranked tags, thus improving the discriminative ability of the learned multi-modality representation. We evaluate our approach on two datasets and show that our proposed RCA-NOC approach outperforms state-of-the-art methods by a large margin, demonstrating its effectiveness in improving vision-language representation for novel object captioning.

Referring expression comprehension aims to localize a natural language description in an image. Using location priors to help reduce inaccuracies in cross-modal alignments is the state of the art for CNN-based methods tackling this problem. Recent Transformer-based models cast aside this idea, making the case for steering away from hand-designed components. In this work, we propose LUNA, which uses language as continuing anchors to guide box prediction in a Transformer decoder, and thus show that language-guided location priors can be effectively exploited in a Transformer-based architecture. Our method first initializes an anchor box from the input expression via a small "proto-decoder,'' and then uses this anchor and its refined successors as location guidance in a modified Transformer decoder. At each decoder layer, the anchor box is first used as a query for gathering multi-modal context, and then updated based on the gathered context (producing the next, refined anchor). In the end, a lightweight assessment pathway evaluates the quality of all produced anchors, yielding the final prediction in a dynamic way. This approach allows box decoding to be conditioned on learned anchors, which facilitates accurate grounding, as we shown in the experiments. Our method outperforms existing state-of-the-art methods on the datasets of ReferIt Game, RefCOCO/+/g, and Flickr30K Entities.

Text visual question answering (TextVQA) targets at answering the question related to texts appearing in the given images, posing more challenges than VQA by requiring a deeper recognition and understanding of various shapes of human-readable scene texts as well as their meanings in different contexts. Existing works on TextVQA suffer from two weaknesses: i) scene texts and non-textual objects are processed separately and independently without considering their mutual interactions during the question understanding and answering process, ii) scene texts are encoded only through word embeddings without taking the corresponding visual appearance features as well as their potential relationships with other non-textual objects in the images into account. To overcome the weakness of existing works, we propose a novel multi-modal contextual graph neural network (MCG) model for TextVQA. The proposed MCG model can capture the relationships between visual features of scene texts and non-textual objects in the given images as well as utilize richer sources of multi-modal features to improve the model performance. In particular, we encode the scene texts into richer features containing textual, visual and positional features, then model the visual relations between scene texts and non-textual objects through a contextual graph neural network. Our extensive experiments on real-world dataset demonstrate the advantages of the proposed MCG model over baseline approaches.

The Internet is more and more integrated into people’s life; because of the complexity and fragility of the network environment, network attack presents a more and more serious trend. Application Layer DDoS (AL-DDoS) attack is the most complex form of DDoS attack, which is hindering the availability for the legitimate users by taking up a large number of requests of web server. The paper introduced the concept of behavior utility to portray the network. The concept of attack and defense utility was defined by a specific property which was the manifestation of the network risk after the offset of attack and defense. In the utility model, traffic metrics were mapped to the multidimensional parallelotope in the Euclidean space to express as a diagonal matrix. To determine the threshold status, the defense strategies of load balancing and limiting the maximum number of connections were used with different attack scales. Finally, the attack and defense utility value was calculated to evaluate the network risk level. The proposed method can master the capacity of network system against each attack means and the defense capability of network system. Its availability and accuracy are verified by comparing with the relevant works.