In recent years, significant developments have been made in both video retrieval and video moment retrieval tasks, which respectively retrieve complete videos or moments for a given text query. These advancements have greatly improved user satisfaction during the search process. However, previous work has failed to establish meaningful ''interaction'' between the retrieval system and the user, and its one-way retrieval paradigm can no longer fully meet the personalization and dynamic needs of at least 80.8% of users. In this paper, we introduce the Interactive Video Corpus Retrieval (IVCR) task, a more realistic setting that enables multi-turn, conversational, and realistic interactions between the user and the retrieval system. To facilitate research on this challenging task, we introduce IVCR-200K, a high-quality, bilingual, multi-turn, conversational, and abstract semantic dataset that supports video retrieval and even moment retrieval. Furthermore, we propose a comprehensive framework based on multi-modal large language models (MLLMs) to help users interact in several modes with more explainable solutions. The extensive experiments demonstrate the effectiveness of our dataset and framework. The datasets, codes, and leaderboards are available at: https://ivcr200k.github.io/IVCR.

Cross-modal video retrieval aims to retrieve semantically relevant videos when given a textual query, and is one of the fundamental multimedia tasks. Most top-performing methods primarily leverage Vision Transformer (ViT) to extract video features (Lei et al., 2021}, (Bain et al., 2021), (Wang et al., 2022). However, they suffer from the high computational complexity of ViT, especially when encoding long videos. A common and simple solution is to uniformly sample a small number (e.g., 4 or 8) of frames from the target video (instead of using the whole video) as ViT inputs. The number of frames has a strong influence on the performance of ViT, e.g., using 8 frames yields better performance than using 4 frames but requires more computational resources, resulting in a trade-off. To get free from this trade-off, this paper introduces an automatic video compression method based on a bilevel optimization program (BOP) consisting of both model-level (i.e., base-level) and frame-level (i.e., meta-level) optimizations. The model-level optimization process learns a cross-modal video retrieval model whose input includes the “compressed frames” learned by frame-level optimization. In turn, frame-level optimization is achieved through gradient descent using the meta loss of the video retrieval model computed on the whole video. We call this BOP method (as well as the “compressed frames”) the Meta-Optimized Frames (MOF) approach. By incorporating MOF, the video retrieval model is able to utilize the information of whole videos (for training) while taking only a small number of input frames in its actual implementation. The convergence of MOF is guaranteed by meta gradient descent algorithms. For evaluation purposes, we conduct extensive cross-modal video retrieval experiments on three large-scale benchmarks: MSR-VTT, MSVD, and DiDeMo. Our results show that MOF is a generic and efficient method that boost multiple baseline methods, and can achieve a new state-of-the-art performance.

The task of temporally language grounding (TLG), aiming to locate a video moment within an untrimmed video that matches a given textual query, has attracted considerable research attention in recent years. Typical retrieval-based TLG methods are inefficient due to their reliance on a large number of pre-segmented candidate moments, while localization-based TLG solutions adopt reinforcement learning, resulting in unstable convergence. Meanwhile, the cutting-edge capabilities of multi-modal architecture, especially pre-training paradigm, have not been fully exploited. Therefore, how to perform TLG task efficiently and stably is a non-trivial task. In this work, we propose a novel TLG solution named Multi-modal Multi-Prompt Tuning (MMPT), which formulates the TLG task as a prompt-based multi-modal problem and integrates multiple sub-tasks to tune the performance. In this way, off-the-shelf pre-trained models can be directly leveraged to achieve more stable performance. Specifically, a flexible multi-prompt strategy is contributed to rewrite the query firstly, which contains the query, the start and end timestamps. Among them, various prompt templates are integrated to enhance robustness. Thereafter, a multi-modal Transformer is adopted to fully learn the multi-modal context. Moreover, we design various sub-tasks to optimize this novel framework including the matching task, localization task and joint learning task. Extensive experiments on two real-world datasets validate the effectiveness and rationality of our proposed solution.

The task of text-video retrieval aims to understand the correspondence between language and vision and has gained increasing attention in recent years. Recent works have demonstrated the superiority of local spatio-temporal relation learning with graph-based models. However, most existing graph-based models are handcrafted and depend heavily on expert knowledge and empirical feedback, which may be unable to mine the high-level fine-grained visual relations effectively. These limitations result in their inability to distinguish videos with the same visual components but different relations. To solve this problem, we propose a novel cross-modal retrieval framework, Bi-Branch Complementary Network (BiC-Net), which modifies Transformer architecture to effectively bridge text-video modalities in a complementary manner via combining local spatio-temporal relation and global temporal information. Specifically, local video representations are encoded using multiple Transformer blocks and additional residual blocks to learn fine-grained spatio-temporal relations and long-term temporal dependency, calling the module a Fine-grained Spatio-temporal Transformer (FST). Global video representations are encoded using a multi-layer Transformer block to learn global temporal features. Finally, we align the spatio-temporal relation and global temporal features with the text feature on two embedding spaces for cross-modal text-video retrieval. Extensive experiments are conducted on MSR-VTT, MSVD, and YouCook2 datasets. The results demonstrate the effectiveness of our proposed model. Our code is public at https://github.com/lionel-hing/BiC-Net .

Given a textual sentence provided by a user, the Temporal Language Grounding (TLG) task is defined as the process of finding a semantically relevant video moment or clip from an untrimmed video. In recent years, localization-based TLG methods have been explored, which adopt reinforcement learning to locate a clip from the video. However, these methods are not stable enough due to the stochastic exploration mechanism of reinforcement learning, which is sensitive to the reward. Therefore, providing a more flexible and reasonable reward has become a focus of attention for both academia and industry.

Cross-modal retrieval between texts and videos has received consistent research interest in the multimedia community. Existing studies follow a trend of learning a joint embedding space to measure the distance between text and video representations. In common practice, video representation is constructed by feeding clips into 3D convolutional neural networks for a coarse-grained global visual feature extraction. In addition, several studies have attempted to align the local objects of video with the text. However, these representations share a drawback of neglecting rich fine-grained relation features capturing spatial-temporal object interactions that benefits mapping textual entities in the real-world retrieval system. To tackle this problem, we propose an adversarial multi-grained embedding network (AME-Net), a novel cross-modal retrieval framework that adopts both fine-grained local relation and coarse-grained global features in bridging text-video modalities. Additionally, with the newly proposed visual representation, we also integrate an adversarial learning strategy into AME-Net, to further narrow the domain gap between text and video representations. In summary, we contribute AME-Net with an adversarial learning strategy for learning a better joint embedding space, and experimental results on MSR-VTT and YouCook2 datasets demonstrate that our proposed framework consistently outperforms the state-of-the-art method.

Despite the recent progress of cross-modal text-to-video retrieval techniques, their performance is still unsatisfactory. Most existing works follow a trend of learning a joint embedding space to measure the distance between global-level or local-level textual and video representation. The fine-grained interactions between video segments and phrases are usually neglected in cross-modal learning, which results in suboptimal retrieval performances. To tackle the problem, we propose a novel Fine-grained Cross-modal Alignment Network (FCA-Net), which considers the interactions between visual semantic units (i.e., sub-actions/sub-events) in videos and phrases in sentences for cross-modal alignment. Specifically, the interactions between visual semantic units and phrases are formulated as a link prediction problem optimized by a graph auto-encoder to obtain the explicit relations between them and enhance the aligned feature representation for fine-grained cross-modal alignment. Experimental results on MSR-VTT, YouCook2, and VATEX datasets demonstrate the superiority of our model as compared to the state-of-the-art method.