Mug-STAN: Adapting Image-Language Pretrained Models for General Video Understanding

Large-scale image-language pretrained models, e.g., CLIP, have demonstrated remarkable proficiency in acquiring general multi-modal knowledge through web-scale image-text data. Despite the impressive performance of image-language models on various image tasks, how to effectively expand them on general video understanding remains an area of ongoing exploration. In this paper, we investigate the image-to-video transferring from the perspective of the model and the data, unveiling two key obstacles impeding the adaptation of image-language models: non-generalizable temporal modeling and partially misaligned video-text data. To address these challenges, we propose Spatial-Temporal Auxiliary Network with Mutual-guided alignment module (Mug-STAN), a simple yet effective framework extending image-text model to diverse video tasks and video-text data.Specifically, STAN adopts a branch structure with decomposed spatial-temporal modules to enable generalizable temporal modeling, while Mug suppresses misalignment by introducing token-wise feature aggregation of either modality from the other. Extensive experimental results verify Mug-STAN significantly improves adaptation of language-image pretrained models such as CLIP and CoCa at both video-text post-pretraining and finetuning stages. With our solution, state-of-the-art zero-shot and finetuning results on various downstream datasets, including MSR-VTT, DiDeMo, LSMDC, Kinetics-400, Something-Something-2, HMDB-51, UCF- 101, and AVA, are achieved. Moreover, by integrating pretrained Mug-STAN with the emerging multimodal dialogue model, we can realize zero-shot video chatting. Codes are available at https://github.com/farewellthree/STAN

Associating Spatially-Consistent Grouping with Text-supervised Semantic Segmentation

In this work, we investigate performing semantic segmentation solely through the training on image-sentence pairs. Due to the lack of dense annotations, existing text-supervised methods can only learn to group an image into semantic regions via pixel-insensitive feedback. As a result, their grouped results are coarse and often contain small spurious regions, limiting the upper-bound performance of segmentation. On the other hand, we observe that grouped results from self-supervised models are more semantically consistent and break the bottleneck of existing methods. Motivated by this, we introduce associate self-supervised spatially-consistent grouping with text-supervised semantic segmentation. Considering the part-like grouped results, we further adapt a text-supervised model from image-level to region-level recognition with two core designs. First, we encourage fine-grained alignment with a one-way noun-to-region contrastive loss, which reduces the mismatched noun-region pairs. Second, we adopt a contextually aware masking strategy to enable simultaneous recognition of all grouped regions. Coupled with spatially-consistent grouping and region-adapted recognition, our method achieves 59.2% mIoU and 32.4% mIoU on Pascal VOC and Pascal Context benchmarks, significantly surpassing the state-of-the-art methods.

Revisiting Temporal Modeling for CLIP-based Image-to-Video Knowledge Transferring

Image-text pretrained models, e.g., CLIP, have shown impressive general multi-modal knowledge learned from large-scale image-text data pairs, thus attracting increasing attention for their potential to improve visual representation learning in the video domain. In this paper, based on the CLIP model, we revisit temporal modeling in the context of image-to-video knowledge transferring, which is the key point for extending image-text pretrained models to the video domain. We find that current temporal modeling mechanisms are tailored to either high-level semantic-dominant tasks (e.g., retrieval) or low-level visual pattern-dominant tasks (e.g., recognition), and fail to work on the two cases simultaneously. The key difficulty lies in modeling temporal dependency while taking advantage of both high-level and low-level knowledge in CLIP model. To tackle this problem, we present Spatial-Temporal Auxiliary Network (STAN) -- a simple and effective temporal modeling mechanism extending CLIP model to diverse video tasks. Specifically, to realize both low-level and high-level knowledge transferring, STAN adopts a branch structure with decomposed spatial-temporal modules that enable multi-level CLIP features to be spatial-temporally contextualized. We evaluate our method on two representative video tasks: Video-Text Retrieval and Video Recognition. Extensive experiments demonstrate the superiority of our model over the state-of-the-art methods on various datasets, including MSR-VTT, DiDeMo, LSMDC, MSVD, Kinetics-400, and Something-Something-V2. Codes will be available at https://github.com/farewellthree/STAN

Temporal Perceiving Video-Language Pre-training

Video-Language Pre-training models have recently significantly improved various multi-modal downstream tasks. Previous dominant works mainly adopt contrastive learning to achieve global feature alignment across modalities. However, the local associations between videos and texts are not modeled, restricting the pre-training models' generality, especially for tasks requiring the temporal video boundary for certain query texts. This work introduces a novel text-video localization pre-text task to enable fine-grained temporal and semantic alignment such that the trained model can accurately perceive temporal boundaries in videos given the text description. Specifically, text-video localization consists of moment retrieval, which predicts start and end boundaries in videos given the text description, and text localization which matches the subset of texts with the video features. To produce temporal boundaries, frame features in several videos are manually merged into a long video sequence that interacts with a text sequence. With the localization task, our method connects the fine-grained frame representations with the word representations and implicitly distinguishes representations of different instances in the single modality. Notably, comprehensive experimental results show that our method significantly improves the state-of-the-art performance on various benchmarks, covering text-to-video retrieval, video question answering, video captioning, temporal action localization and temporal moment retrieval. The code will be released soon.

Class Prototype-based Cleaner for Label Noise Learning

Semi-supervised learning based methods are current SOTA solutions to the noisy-label learning problem, which rely on learning an unsupervised label cleaner first to divide the training samples into a labeled set for clean data and an unlabeled set for noise data. Typically, the cleaner is obtained via fitting a mixture model to the distribution of per-sample training losses. However, the modeling procedure is \emph{class agnostic} and assumes the loss distributions of clean and noise samples are the same across different classes. Unfortunately, in practice, such an assumption does not always hold due to the varying learning difficulty of different classes, thus leading to sub-optimal label noise partition criteria. In this work, we reveal this long-ignored problem and propose a simple yet effective solution, named \textbf{C}lass \textbf{P}rototype-based label noise \textbf{C}leaner (\textbf{CPC}). Unlike previous works treating all the classes equally, CPC fully considers loss distribution heterogeneity and applies class-aware modulation to partition the clean and noise data. CPC takes advantage of loss distribution modeling and intra-class consistency regularization in feature space simultaneously and thus can better distinguish clean and noise labels. We theoretically justify the effectiveness of our method by explaining it from the Expectation-Maximization (EM) framework. Extensive experiments are conducted on the noisy-label benchmarks CIFAR-10, CIFAR-100, Clothing1M and WebVision. The results show that CPC consistently brings about performance improvement across all benchmarks. Codes and pre-trained models will be released at \url{https://github.com/hjjpku/CPC.git}.

Knowledge Guided Bidirectional Attention Network for Human-Object Interaction Detection

Human Object Interaction (HOI) detection is a challenging task that requires to distinguish the interaction between a human-object pair. Attention based relation parsing is a popular and effective strategy utilized in HOI. However, current methods execute relation parsing in a "bottom-up" manner. We argue that the independent use of the bottom-up parsing strategy in HOI is counter-intuitive and could lead to the diffusion of attention. Therefore, we introduce a novel knowledge-guided top-down attention into HOI, and propose to model the relation parsing as a "look and search" process: execute scene-context modeling (i.e. look), and then, given the knowledge of the target pair, search visual clues for the discrimination of the interaction between the pair. We implement the process via unifying the bottom-up and top-down attention in a single encoder-decoder based model. The experimental results show that our model achieves competitive performance on the V-COCO and HICO-DET datasets.

Clover: Towards A Unified Video-Language Alignment and Fusion Model

Building a universal video-language model for solving various video understanding tasks (e.g., text-video retrieval, video question answering) is an open challenge to the machine learning field. Towards this goal, most recent attempts train the models, usually consisting of uni-modal and cross-modal feature encoders, with supervised or pair-wise contrastive pre-text tasks. Though offering attractive generality, the resulted models have to compromise between efficiency and performance. We argue the flaws are caused by their pre-training strategies\textemdash they cannot well align and fuse features from different modalities simultaneously. We then introduce Clover -- a Correlated Video-Language pre-training method -- towards a universal video-language model for solving multiple video understanding tasks with neither performance nor efficiency compromise. It improves cross-modal feature alignment and fusion via a novel tri-modal alignment pre-training task. Additionally, we propose to enhance the tri-modal alignment via incorporating learning from masked samples and a novel pair-wise ranking loss. Clover demonstrates outstanding generality. It establishes new state-of-the-arts on multiple downstream tasks, including three retrieval tasks for both zero-shot and fine-tuning settings, and eight video question answering tasks. Codes and pre-trained models will be released at https://github.com/LeeYN-43/Clover.

ARMIN: Towards a More Efficient and Light-weight Recurrent Memory Network

In recent years, memory-augmented neural networks(MANNs) have shown promising power to enhance the memory ability of neural networks for sequential processing tasks. However, previous MANNs suffer from complex memory addressing mechanism, making them relatively hard to train and causing computational overheads. Moreover, many of them reuse the classical RNN structure such as LSTM for memory processing, causing inefficient exploitations of memory information. In this paper, we introduce a novel MANN, the Auto-addressing and Recurrent Memory Integrating Network (ARMIN) to address these issues. The ARMIN only utilizes hidden state ht for automatic memory addressing, and uses a novel RNN cell for refined integration of memory information. Empirical results on a variety of experiments demonstrate that the ARMIN is more light-weight and efficient compared to existing memory networks. Moreover, we demonstrate that the ARMIN can achieve much lower computational overhead than vanilla LSTM while keeping similar performances. Codes are available on github.com/zoharli/armin.

A Self-Adaptive Proposal Model for Temporal Action Detection based on Reinforcement Learning

Existing action detection algorithms usually generate action proposals through an extensive search over the video at multiple temporal scales, which brings about huge computational overhead and deviates from the human perception procedure. We argue that the process of detecting actions should be naturally one of observation and refinement: observe the current window and refine the span of attended window to cover true action regions. In this paper, we propose an active action proposal model that learns to find actions through continuously adjusting the temporal bounds in a self-adaptive way. The whole process can be deemed as an agent, which is firstly placed at a position in the video at random, adopts a sequence of transformations on the current attended region to discover actions according to a learned policy. We utilize reinforcement learning, especially the Deep Q-learning algorithm to learn the agent's decision policy. In addition, we use temporal pooling operation to extract more effective feature representation for the long temporal window, and design a regression network to adjust the position offsets between predicted results and the ground truth. Experiment results on THUMOS 2014 validate the effectiveness of the proposed approach, which can achieve competitive performance with current action detection algorithms via much fewer proposals.