Visual instruction tuning is a key training stage of large multimodal models. However, when learning multiple visual tasks simultaneously, this approach often results in suboptimal and imbalanced overall performance due to latent knowledge conflicts across tasks. To mitigate this issue, we propose a novel Adaptive Task Balancing approach tailored for visual instruction tuning (VisATB). Specifically, we measure two critical dimensions for visual task balancing based on validation performance: (1) Inter-Task Contribution, the mechanism where learning one task enhances the performance on others owing to shared knowledge across tasks, and (2) Intra-Task Difficulty, which denotes the inherent learning difficulty of a single task. Furthermore, we propose prioritizing three categories of tasks with greater weight: those that offer substantial contributions to others, those that receive minimal contributions from others, and those that present high learning difficulties. Among these three task weighting strategies, the first and third focus on improving overall performance, and the second targets the mitigation of performance imbalance. Extensive experiments on three benchmarks demonstrate that our VisATB approach consistently achieves superior and more balanced overall performance in visual instruction tuning. The data, code, and models are available at https://github.com/YanqiDai/VisATB.

Class-Incremental Learning (Class-IL) aims to continuously learn new knowledge without forgetting old knowledge from a given data stream in the realm of image classification. Recent Class-IL methods strive to balance old and new knowledge and have achieved excellent results in mitigating the forgetting by mainly employing the rehearsal-based strategy. However, the representation learning on new tasks is often impaired since the trade-off is hard to taken between old and new knowledge. To overcome this challenge, based on the Complementary Learning System (CLS) theory, we propose a novel CLS-based method by focusing on the representation of old and new knowledge under the Class-IL setting, which can acquire more new knowledge from new tasks while consolidating the old knowledge so as to make a better balance between them (i.e., enhancing the overall model performance). Specifically, our proposed method has two novel components: (1) To effectively mitigate the forgetting, we first propose a bidirectional transport (BDT) strategy between old and new models, which can better integrate the old knowledge into the new knowledge and meanwhile enforce the old knowledge to be better consolidated by bidirectionally transferring parameters across old and new models. (2) To ensure that the representation of new knowledge is not impaired by the old knowledge, we further devise a selective momentum (SMT) mechanism to give parameters greater flexibility to learn new knowledge while transferring important old knowledge, which is achieved by selectively (momentum) updating network parameters through parameter importance evaluation. Extensive experiments on five benchmarks show that our proposed method significantly outperforms the state-of-the-arts under the Class-IL setting.

Continual learning aims to learn a sequence of tasks without forgetting the previously learned knowledge. Although existing memory-based approaches can be easily deployed for video Class-Incremental Learning (CIL), little efforts have been made to explore how to better exploit the data from the previous work (in the memory) for alleviating the catastrophic forgetting. In this work, we thus propose a simple yet effective framework called Mixup-Inspired Video Class-Incremental Learning (MIV-CIL). The core idea of our MIVCIL framework is to impose mixup on the current video data and the previous video data (from the memory buffer) to mitigate the catastrophic forgetting. By exploring different mixup strategies on the video data, our MIVCIL framework has three instantiations for video class-incremental learning. We further provide a detailed analysis of the performance and computational overhead of the three instantiations on the latest benchmark vCLIMB. Experimental results show that all three instantiations achieve significant improvements over the representative/state-of-the-art methods.

Video-text retrieval has drawn great attention due to the prosperity of online video contents. Most existing methods extract the video embeddings by densely sampling abundant (generally dozens of) video clips, which acquires tremendous computational cost. To reduce the resource consumption, recent works propose to sparsely sample fewer clips from each raw video with a narrow time span. However, they still struggle to learn a reliable video representation with such locally sampled video clips, especially when testing on cross-dataset setting. In this work, to overcome this problem, we sparsely and globally (with wide time span) sample a handful of video clips from each raw video, which can be regarded as different samples of a pseudo video class (i.e., each raw video denotes a pseudo video class). From such viewpoint, we propose a novel Cross-Modal Meta-Transformer (CMMT) model that can be trained in a meta-learning paradigm. Concretely, in each training step, we conduct a cross-modal fine-grained classification task where the text queries are classified with pseudo video class prototypes (each has aggregated all sampled video clips per pseudo video class). Since each classification task is defined with different/new videos (by simulating the evaluation setting), this task-based meta-learning process enables our model to generalize well on new tasks and thus learn generalizable video/text representations. To further enhance the generalizability of our model, we induce a token-aware adaptive Transformer module to dynamically update our model (prototypes) for each individual text query. Extensive experiments on three benchmarks show that our model achieves new state-of-the-art results in cross-dataset video-text retrieval, demonstrating that it has more generalizability in video-text retrieval. Importantly, we find that our new meta-learning paradigm indeed brings improvements under both cross-dataset and in-dataset retrieval settings.

In realistic application scenarios, existing methods for image-text modeling have limitations in dealing with data stream: training on all data needs too much computation/storage resources, and even the full access to previous data is invalid. In this work, we thus propose a new continual image-text modeling (CITM) setting that requires a model to be trained sequentially on a number of diverse image-text datasets. Although recent continual learning methods can be directly applied to the CITM setting, most of them only consider reusing part of previous data or aligning the output distributions of previous and new models, which is a partial or indirect way to acquire the old knowledge. In contrast, we propose a novel dynamic historical adaptation (DHA) method which can holistically and directly review the old knowledge from a historical model. Concretely, the historical model transfers its total parameters to the main/current model to utilize the holistic old knowledge. In turn, the main model dynamically transfers its parameters to the historical model at every five training steps to ensure that the knowledge gap between them is not too large. Extensive experiments show that our proposed DHA outperforms other representative/latest continual learning methods under the CITM setting.

With the development of video sharing websites, numerous users desire to create their own attractive video montages. However, it is difficult for inexperienced users to create well-edited video montages due to the lack of professional expertise. In the meantime, it is time-consuming even for experts to create video montages of high quality, which requires effectively selecting shots from abundant candidates and assembling them together. Instead of manual creation, various automatic methods have been proposed for video montage generation, which typically take a single sentence as input for text-to-shot retrieval, and ignore the semantic cross-sentence coherence given complicated text script of multiple sentences. To overcome this drawback, we propose a novel model for video montage generation by retrieving and assembling shots with arbitrary text scripts. To this end, a sequence consistency transformer is devised for cross-sentence coherence modeling. More importantly, with this transformer, two novel sequence-level tasks are defined for sentence-shot alignment in sequence-level: Cross-Modal Sequence Matching (CMSM) task, and Chaotic Sequence Recovering (CSR) task. To facilitate the research on video montage generation, we construct a new, highly-varied dataset which collects thousands of video-script pairs in documentary. Extensive experiments on the constructed dataset demonstrate the superior performance of the proposed model. The dataset and generated video demos are available at https://github.com/RATVDemo/RATV.

We bring the novel idea of exploiting motifs into network embedding, in a dual-level network representation learning model called RUM (network Representation learning Using Motifs). Towards the leveraging of graph motifs that constitute higher-order organizations in a network, we propose two strategies, namely MotifWalk and MotifRe-weighting for learning motif-aware network embeddings. Motif-based and node-based representations are simultaneously generated, so that both the high-order structures and each node's individual properties are preserved in the final embeddings. We demonstrate that RUM has strong and well-balanced capability of preserving lowerorder proximities while discovering and capturing higher-order network structures. In empirical evaluation, RUM is tested on multiple public datasets, that range from small to medium citation networks to a large social network with more than a million nodes. Results show that the use of motifs in the representation learning process brings substantial benefits in reallife tasks, resulting in up to 12% microF1 and 8% macroF1 relative gains for node classification performance over the bestperforming competing methods.

Fine-grained image classification and retrieval become topical in both computer vision and information retrieval. In real-life scenarios, fine-grained tasks tend to appear along with coarse-grained tasks when the observed object is coming closer. However, in previous works, the combination of fine-grained and coarse-grained tasks was often ignored. In this paper, we define a new problem called coarse-to-fine grained classification (C2FGC) which aims to recognize the classes of objects in multiple resolutions (from low to high). To solve this problem, we propose a novel Multi-linear Pooling with Hierarchy (MLPH) model. Specifically, we first design a multi-linear pooling module to include both trilinear and bilinear pooling, and then formulate the coarse-grained and fine-grained tasks within a unified framework. Experiments on two benchmark datasets show that our model achieves state-of-the-art results.

This paper presents a graph-based method for heterogeneous constraint propagation on multi-modal data using constrained sparse representation. Since heterogeneous pair wise constraints are defined over pairs of data points from different modalities, heterogeneous constraint propagation is more challenging than the transitional homogeneous constraint propagation on single-modal data which has been studied extensively in previous work. The main difficulty of heterogeneous constraint propagation lies in how to effectively propagate heterogeneous pair wise constraints across different modalities. To address this issue, we decompose heterogeneous constraint propagation into semi-supervised learning sub problems which can then be efficiently solved by graph-based label propagation. Moreover, we develop a constrained sparse representation method for graph construction over each modality using homogeneous pair wise constraints. The experimental results in cross-modal retrieval have shown the superior performance of our heterogeneous constraint propagation.